MCP servers › ai.securenow › securenow

MCP server · registry snapshot 2026-10-23 · last tested 2026-10-23

ai.securenow/securenow

Production security for Node.js apps: investigate live attacks, block IPs, tune detections. — the publisher's description

6 of 9 record checks metRead-only · tools listed 2026-10-23Topic: security · AI-classifiedversion 8.12.4JavaScriptISCstandard input/output, streamable HTTP90 tools

Summary

ai.securenow/securenow is a remote and local MCP server listed in the official MCP registry at version 8.12.4. On 2026-10-23 ProtocolProbe started its published package in an isolated sandbox in read-only mode and read its inventory: 90 tools, 5 resources and 9 prompts.

Record checks

6 of 9 record checks met

met: Registry entry is active and says how to run it
met: Source repository link opens
met: Repository is not archived
not met: Code pushed to the repository in the 90 days before our check
not met: Repository publishes a security policy (SECURITY.md)
met: Package names its licence with a standard (SPDX) identifier
met: The version the registry lists can be installed and is not withdrawn
not met: npm package carries build provenance (attestation)
met: No known critical or high advisory in the package or its dependencies

#1,418 of 15,115 packages by monthly downloads, tied with 1 other
Not ranked by stars: 0 stars (ranked from 10)

From public records, not a safety rating. Each check with its reason · Is it safe to install?

Key facts

Runs: remote and local package
Transport: standard input/output, streamable HTTP
Package: npm · listed version current
License: ISC
Dependencies: no known high or critical advisories
Repository: public
Tools: 90
Described as changing data: 43 of 90 toolsAI-classified
Mainly works on: accounts and data in outside web services; cloud accounts, servers or DevOps toolsAI-classified
Topic: securityAI-classified
Last tested: 2026-10-23

Add to your client

Worth knowing before you connect it

43 tools are described as changing something (securenow_apps_create, securenow_firewall_enable, securenow_firewall_disable, …): our AI model's reading of the descriptions, not something we tested. We did not call them.

Each line comes from a section below, with its source and date.

How fresh this is

Live-tested: yes, a real session (not a text-only review)
Last tested: 2026-10-23
Mode: read-only (no tool calls)
Latest version: 8.12.4, published 2026-10-19 (registry, as of the 2026-10-23 snapshot)
First listed version: 2026-10-19 (earliest version still in the registry; older removed versions would be earlier)
Registry data: snapshot 2026-10-23
Package and repository: checked 2026-10-22
Engine: mcp-runtime-engine@0.1.0 · sdk@1.32.0

Changes since the last refresh

New in the registry: not in the list of 2026-10-04, listed on 2026-10-23 with version 8.12.4 (published 2026-10-19).

Source: the official MCP Registry list on 2026-10-04 and on 2026-10-23.

What it is

What does this server offer?

Observed inventory

90tools

5resources

9prompts

What it mainly works on, as our AI model read its tool descriptions: accounts and data in outside web services; cloud accounts, servers or DevOps tools.

43 of 90 tools are described as changing something (creating, editing, deleting, sending or running).

securenow_auth_statusreads or searches
“Show local SecureNow credential source, selected app, and masked runtime API key.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
securenow_apps_listreads or searches
“List SecureNow applications for the authenticated user.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
securenow_apps_createcreates or changes datadescribed as changing data
“Create a SecureNow application.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 3 required
- namestringrequired“Application name.”
- hostsarray“Optional hostnames/domains for this application.”
- instanceIdstring“Optional ClickHouse instance id.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_apps_inforeads or searches
“Get details for an application by app key.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- keystringrequired“Application key UUID.”
securenow_firewall_appsreads or searches
“List applications with firewall toggle and SecureNow AI IPDB threshold state.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
securenow_firewall_statusreads or searches
“Show firewall blocklist/allowlist status for the authenticated account.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- appKeystring“Optional application key UUID to scope the status check.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
securenow_firewall_enabledescribed as changing data
“Turn the per-app firewall ON.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
4 inputs, 3 required
- appKeystringrequired“Application key UUID.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_firewall_disabledescribed as changing data
“Turn the per-app firewall OFF.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
4 inputs, 3 required
- appKeystringrequired“Application key UUID.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_firewall_set_thresholddescribed as changing data
“Set the per-app SecureNow AI IPDB confidence threshold.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
5 inputs, 4 required
- appKeystringrequired“Application key UUID.”
- confidenceMinimumnumberrequired“Minimum SecureNow AI IPDB confidence score.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_firewall_test_ipreads or searches
“Check whether an IP would be blocked by the firewall.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- ipstringrequired“IPv4 address to test.”
- appKeystring“Optional application key UUID to test the app/environment toggle and scoped lists.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
securenow_traces_listreads or searches
“List recent traces for one or more applications.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 1 required
- appKeysstring or arrayrequired“Application key or comma-separated/list of application keys.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
- fromstring“Start time as ISO 8601, optional.”
- tostring“End time as ISO 8601, optional.”
- limitnumber“Maximum traces to return.”
securenow_traces_showreads or searches
“Show spans for a trace id scoped to one or more app keys.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
- traceIdstringrequired“Trace id.”
- appKeysstring or arrayrequired“Application key or comma-separated/list of application keys.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”

Show 78 more tools

securenow_logs_listreads or searches
“List recent logs for one or more applications.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs, 1 required
- appKeysstring or arrayrequired“Application key or comma-separated/list of application keys.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
- fromstring“Start time as ISO 8601, optional.”
- tostring“End time as ISO 8601, optional.”
- severitystring“Optional severity filter.”
- limitnumber“Maximum logs to return.”
securenow_logs_for_tracereads or searches
“Show logs correlated to a trace id.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 2 required
- traceIdstringrequired“Trace id.”
- appKeysstring or arrayrequired“Application key or comma-separated/list of application keys.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
securenow_notifications_listreads or searches
“List security notifications.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- limitnumber“Maximum results to return.”
- pagenumber“Page number.”
securenow_notifications_unreadreads or searches
“Return unread notification count.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
securenow_notifications_readcreates or changes datadescribed as changing data
“Mark a notification as read.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
3 inputs, 3 required
- idstringrequired“Notification id.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_notifications_getreads or searches
“Get one notification/case with alert context, clusters, and IP investigations.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstringrequired“Notification id.”
securenow_notifications_batch_getreads or searches
“Fetch multiple notification/case records in one request.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idsarrayrequired“Notification ids to fetch, up to 50.”
securenow_human_actions_listreads or searches
“List approval-gated human decisions prepared by SecureNow AI, ordered by urgency.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- limitnumber“Maximum results to return.”
- pagenumber“Page number.”
- searchstring“Optional search over IP, rule, path, or verdict.”
securenow_human_actions_grouped_listreads or searches
“List Requires Human work as root-cause groups with batch-safety preview instead of one row per IP/action.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- limitnumber“Maximum results to return.”
- pagenumber“Page number.”
- searchstring“Optional search over IP, rule, path, action, or verdict.”
securenow_alert_review_runs_listreads or searches
“List pending alert-review runs as root-cause groups with batch-action preview, rather than row-by-row noisy alert triage.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs
- limitnumber“Maximum results to return.”
- pagenumber“Page number.”
- searchstring“Optional search over rule, route, IP, evidence, or proposed guard.”
- rootCauseKeystring“Optional root-cause group key to filter to one group.”
- groupKeystring“Compatibility alias for rootCauseKey.”
- includeRunsboolean“Whether to include compact matching run rows in the response.”
- maxScannumber“Maximum pending-review rows to scan before grouping.”
securenow_alert_review_runs_countreads or searches
“Count pending alert-review rows and the root-cause groups they collapse into.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- searchstring“Optional search over rule, route, IP, evidence, or proposed guard.”
- maxScannumber“Maximum pending-review rows to scan before grouping.”
securenow_alert_review_run_getreads or searches
“Fetch one pending-review alert run with its root-cause key, evidence-quality score, and similar open siblings.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- idstringrequired“Notification id for the alert review run.”
- maxScannumber“Maximum pending-review rows to scan for similar siblings.”
securenow_alert_review_run_resolvecreates or changes datadescribed as changing data
“Close one pending alert-review row with an auditable no-write decision report.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
16 inputs, 3 required
- idstringrequired“Notification id for the alert review run.”
- decisionReportobject“Structured audit report explaining the decision, evidence reviewed, trace IDs, missing proof, and recommendations.”
- decisionSummarystring“Short decision summary to record on the IP/case history.”
- outcomestring“Decision outcome: blocked, rate_limited, false_positive, clean, deferred, case_action, rule_tuning, new_alert_rule, ambiguous, skipped, or other.”
- evidencearray“Evidence strings that support the decision.”
- reviewedHistoryarray“History/proofs reviewed before deciding.”
- traceIdsarray“Trace IDs reviewed for this decision.”
- pathsarray“Paths/endpoints reviewed for this decision.”
- ipsarray“IP addresses affected by this case-level decision report.”
- methodsarray“HTTP methods reviewed for this decision.”
- statusCodesarray“HTTP status codes reviewed for this decision.”
- userAgentsarray“User agents reviewed for this decision.”
- missingProofarray“Proof that was missing when the row is skipped or ambiguous.”
- recommendationsarray“Follow-up recommendations to record with the decision.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_review_run_dismisscreates or changes datadescribed as changing data
“Dismiss one pending alert-review row with an audit report and no enforcement write.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
16 inputs, 3 required
- idstringrequired“Notification id for the alert review run.”
- decisionReportobject“Structured audit report explaining the decision, evidence reviewed, trace IDs, missing proof, and recommendations.”
- decisionSummarystring“Short decision summary to record on the IP/case history.”
- outcomestring“Decision outcome: blocked, rate_limited, false_positive, clean, deferred, case_action, rule_tuning, new_alert_rule, ambiguous, skipped, or other.”
- evidencearray“Evidence strings that support the decision.”
- reviewedHistoryarray“History/proofs reviewed before deciding.”
- traceIdsarray“Trace IDs reviewed for this decision.”
- pathsarray“Paths/endpoints reviewed for this decision.”
- ipsarray“IP addresses affected by this case-level decision report.”
- methodsarray“HTTP methods reviewed for this decision.”
- statusCodesarray“HTTP status codes reviewed for this decision.”
- userAgentsarray“User agents reviewed for this decision.”
- missingProofarray“Proof that was missing when the row is skipped or ambiguous.”
- recommendationsarray“Follow-up recommendations to record with the decision.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_review_run_keep_alivecreates or changes datadescribed as changing data
“Mark the noisy/paused alert rule as reviewed, keep it active, and close the pending alert-review row with an audit report.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
17 inputs, 3 required
- idstringrequired“Notification id for the alert review run.”
- reviewNotestring“Optional rule-review note.”
- decisionReportobject“Structured audit report explaining the decision, evidence reviewed, trace IDs, missing proof, and recommendations.”
- decisionSummarystring“Short decision summary to record on the IP/case history.”
- outcomestring“Decision outcome: blocked, rate_limited, false_positive, clean, deferred, case_action, rule_tuning, new_alert_rule, ambiguous, skipped, or other.”
- evidencearray“Evidence strings that support the decision.”
- reviewedHistoryarray“History/proofs reviewed before deciding.”
- traceIdsarray“Trace IDs reviewed for this decision.”
- pathsarray“Paths/endpoints reviewed for this decision.”
- ipsarray“IP addresses affected by this case-level decision report.”
- methodsarray“HTTP methods reviewed for this decision.”
- statusCodesarray“HTTP status codes reviewed for this decision.”
- userAgentsarray“User agents reviewed for this decision.”
- missingProofarray“Proof that was missing when the row is skipped or ambiguous.”
- recommendationsarray“Follow-up recommendations to record with the decision.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_review_run_apply_group_decisioncreates or changes datadescribed as changing data
“Apply one verified no-write decision report to every currently matching alert-review row in a root-cause group, leaving non-matching rows open.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
25 inputs, 2 required
- rootCauseKeystring“Root-cause group key from securenow_alert_review_runs_list.”
- groupKeystring“Compatibility alias for rootCauseKey.”
- prototypeRunIdstring“Optional notification id whose root-cause key should be used.”
- notificationIdsarray“Optional subset of eligible notification ids to close.”
- statusstring“Resolution status: resolved or dismissed.”
- allowMixedboolean“Allow a mixed decision/attribution group only after every row was manually reviewed.”
- previewOnlyboolean“When true, returns the eligible rows without writing.”
- maxRowsnumber“Maximum rows to close in this batch.”
- maxScannumber“Maximum pending-review rows to scan before grouping.”
- searchstring“Optional search filter applied before grouping.”
- decisionReportobject“Structured audit report explaining the decision, evidence reviewed, trace IDs, missing proof, and recommendations.”
- decisionSummarystring“Short decision summary to record on the IP/case history.”
- outcomestring“Decision outcome: blocked, rate_limited, false_positive, clean, deferred, case_action, rule_tuning, new_alert_rule, ambiguous, skipped, or other.”
- evidencearray“Evidence strings that support the decision.”
- reviewedHistoryarray“History/proofs reviewed before deciding.”
- traceIdsarray“Trace IDs reviewed for this decision.”
- pathsarray“Paths/endpoints reviewed for this decision.”
- ipsarray“IP addresses affected by this case-level decision report.”
- methodsarray“HTTP methods reviewed for this decision.”
- statusCodesarray“HTTP status codes reviewed for this decision.”
- userAgentsarray“User agents reviewed for this decision.”
- missingProofarray“Proof that was missing when the row is skipped or ambiguous.”
- recommendationsarray“Follow-up recommendations to record with the decision.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_review_apply_group_decisioncreates or changes datadescribed as changing data
“Compatibility alias for securenow_alert_review_run_apply_group_decision.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
25 inputs, 2 required
- rootCauseKeystring“Root-cause group key from securenow_alert_review_runs_list.”
- groupKeystring“Compatibility alias for rootCauseKey.”
- prototypeRunIdstring“Optional notification id whose root-cause key should be used.”
- notificationIdsarray“Optional subset of eligible notification ids to close.”
- statusstring“Resolution status: resolved or dismissed.”
- allowMixedboolean“Allow a mixed decision/attribution group only after every row was manually reviewed.”
- previewOnlyboolean“When true, returns the eligible rows without writing.”
- maxRowsnumber“Maximum rows to close in this batch.”
- maxScannumber“Maximum pending-review rows to scan before grouping.”
- searchstring“Optional search filter applied before grouping.”
- decisionReportobject“Structured audit report explaining the decision, evidence reviewed, trace IDs, missing proof, and recommendations.”
- decisionSummarystring“Short decision summary to record on the IP/case history.”
- outcomestring“Decision outcome: blocked, rate_limited, false_positive, clean, deferred, case_action, rule_tuning, new_alert_rule, ambiguous, skipped, or other.”
- evidencearray“Evidence strings that support the decision.”
- reviewedHistoryarray“History/proofs reviewed before deciding.”
- traceIdsarray“Trace IDs reviewed for this decision.”
- pathsarray“Paths/endpoints reviewed for this decision.”
- ipsarray“IP addresses affected by this case-level decision report.”
- methodsarray“HTTP methods reviewed for this decision.”
- statusCodesarray“HTTP status codes reviewed for this decision.”
- userAgentsarray“User agents reviewed for this decision.”
- missingProofarray“Proof that was missing when the row is skipped or ambiguous.”
- recommendationsarray“Follow-up recommendations to record with the decision.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_review_group_similarreads or searches
“Fetch the current rows in one alert-review root-cause group for preview before a batch decision.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs
- rootCauseKeystring“Root-cause group key from securenow_alert_review_runs_list.”
- groupKeystring“Compatibility alias for rootCauseKey.”
- maxScannumber“Maximum pending-review rows to scan before grouping.”
securenow_human_action_reportreads or searches
“Fetch the full IP investigation report, investigation steps, proofs, metadata, and AI decision for one human action row.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- notificationIdstringrequired“Notification id from the human action row.”
- ipstringrequired“IP address from the human action row.”
securenow_human_action_blockdescribed as changing data
“Approve the AI-prepared block decision for an IP and optionally attach a structured decision report to the IP history.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
20 inputs, 4 required
- notificationIdstringrequired“Notification id from the human action row.”
- ipstringrequired“IP address to block.”
- notestring“Audit note explaining why the AI block was approved.”
- verdictstring“Optional final verdict text.”
- riskScorenumber“Optional risk score.”
- decisionReportobject“Structured audit report explaining the decision, evidence reviewed, trace IDs, missing proof, and recommendations.”
- decisionSummarystring“Short decision summary to record on the IP/case history.”
- outcomestring“Decision outcome: blocked, rate_limited, false_positive, clean, deferred, case_action, rule_tuning, new_alert_rule, ambiguous, skipped, or other.”
- evidencearray“Evidence strings that support the decision.”
- reviewedHistoryarray“History/proofs reviewed before deciding.”
- traceIdsarray“Trace IDs reviewed for this decision.”
- pathsarray“Paths/endpoints reviewed for this decision.”
- ipsarray“IP addresses affected by this case-level decision report.”
- methodsarray“HTTP methods reviewed for this decision.”
- statusCodesarray“HTTP status codes reviewed for this decision.”
- userAgentsarray“User agents reviewed for this decision.”
- missingProofarray“Proof that was missing when the row is skipped or ambiguous.”
- recommendationsarray“Follow-up recommendations to record with the decision.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_human_action_decision_report_addcreates or changes datadescribed as changing data
“Attach a structured analyst/MCP decision report to one Requires Human IP row without changing its status.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
17 inputs, 4 required
- notificationIdstringrequired“Notification id from the human action row.”
- ipstringrequired“IP address for the report.”
- decisionReportobject“Structured audit report explaining the decision, evidence reviewed, trace IDs, missing proof, and recommendations.”
- decisionSummarystring“Short decision summary to record on the IP/case history.”
- outcomestring“Decision outcome: blocked, rate_limited, false_positive, clean, deferred, case_action, rule_tuning, new_alert_rule, ambiguous, skipped, or other.”
- evidencearray“Evidence strings that support the decision.”
- reviewedHistoryarray“History/proofs reviewed before deciding.”
- traceIdsarray“Trace IDs reviewed for this decision.”
- pathsarray“Paths/endpoints reviewed for this decision.”
- ipsarray“IP addresses affected by this case-level decision report.”
- methodsarray“HTTP methods reviewed for this decision.”
- statusCodesarray“HTTP status codes reviewed for this decision.”
- userAgentsarray“User agents reviewed for this decision.”
- missingProofarray“Proof that was missing when the row is skipped or ambiguous.”
- recommendationsarray“Follow-up recommendations to record with the decision.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_human_action_close_no_writecreates or changes datadescribed as changing data
“Close one Requires Human IP row with an auditable no-write decision report.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
17 inputs, 4 required
- notificationIdstringrequired“Notification id from the human action row.”
- ipstringrequired“IP address for the row to close.”
- decisionReportobject“Structured audit report explaining the decision, evidence reviewed, trace IDs, missing proof, and recommendations.”
- decisionSummarystring“Short decision summary to record on the IP/case history.”
- outcomestring“Decision outcome: blocked, rate_limited, false_positive, clean, deferred, case_action, rule_tuning, new_alert_rule, ambiguous, skipped, or other.”
- evidencearray“Evidence strings that support the decision.”
- reviewedHistoryarray“History/proofs reviewed before deciding.”
- traceIdsarray“Trace IDs reviewed for this decision.”
- pathsarray“Paths/endpoints reviewed for this decision.”
- ipsarray“IP addresses affected by this case-level decision report.”
- methodsarray“HTTP methods reviewed for this decision.”
- statusCodesarray“HTTP status codes reviewed for this decision.”
- userAgentsarray“User agents reviewed for this decision.”
- missingProofarray“Proof that was missing when the row is skipped or ambiguous.”
- recommendationsarray“Follow-up recommendations to record with the decision.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_human_action_false_positivedescribed as changing data
“Mark an AI-prepared human action as a scoped false positive and optionally attach a structured decision report to the IP history.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
24 inputs, 4 required
- notificationIdstringrequired“Notification id from the human action row.”
- ipstringrequired“IP address to mark as false positive.”
- conditionsarray“Restrictive false-positive conditions.”
- matchModestring“Condition match mode: all or any.”
- createExclusionboolean“Whether to create a restrictive exclusion rule.”
- applyToExistingboolean“Whether to apply to existing matching IP investigations.”
- ruleScopestring“Scope: this_rule, specific_rules, all_existing, or any_rule.”
- targetRuleIdsarray“Specific rule ids when ruleScope is specific_rules.”
- aiConfidencenumber“AI confidence for audit metadata.”
- decisionReportobject“Structured audit report explaining the decision, evidence reviewed, trace IDs, missing proof, and recommendations.”
- decisionSummarystring“Short decision summary to record on the IP/case history.”
- outcomestring“Decision outcome: blocked, rate_limited, false_positive, clean, deferred, case_action, rule_tuning, new_alert_rule, ambiguous, skipped, or other.”
- evidencearray“Evidence strings that support the decision.”
- reviewedHistoryarray“History/proofs reviewed before deciding.”
- traceIdsarray“Trace IDs reviewed for this decision.”
- pathsarray“Paths/endpoints reviewed for this decision.”
- ipsarray“IP addresses affected by this case-level decision report.”
- methodsarray“HTTP methods reviewed for this decision.”
- statusCodesarray“HTTP status codes reviewed for this decision.”
- userAgentsarray“User agents reviewed for this decision.”
- missingProofarray“Proof that was missing when the row is skipped or ambiguous.”
- recommendationsarray“Follow-up recommendations to record with the decision.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_human_case_action_updatedescribed as changing data
“Approve, reject, execute, or fail a case-level proposed action such as tune_rule or create_exclusion.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
19 inputs, 5 required
- notificationIdstringrequired“Notification id from the case-action row.”
- actionKeystringrequired“Proposed action key from the row, for example tune_rule:...”
- statusstringrequired“New status: proposed, approved, rejected, executed, or failed.”
- resultobject“Optional structured result/audit details.”
- decisionReportobject“Structured audit report explaining the decision, evidence reviewed, trace IDs, missing proof, and recommendations.”
- decisionSummarystring“Short decision summary to record on the IP/case history.”
- outcomestring“Decision outcome: blocked, rate_limited, false_positive, clean, deferred, case_action, rule_tuning, new_alert_rule, ambiguous, skipped, or other.”
- evidencearray“Evidence strings that support the decision.”
- reviewedHistoryarray“History/proofs reviewed before deciding.”
- traceIdsarray“Trace IDs reviewed for this decision.”
- pathsarray“Paths/endpoints reviewed for this decision.”
- ipsarray“IP addresses affected by this case-level decision report.”
- methodsarray“HTTP methods reviewed for this decision.”
- statusCodesarray“HTTP status codes reviewed for this decision.”
- userAgentsarray“User agents reviewed for this decision.”
- missingProofarray“Proof that was missing when the row is skipped or ambiguous.”
- recommendationsarray“Follow-up recommendations to record with the decision.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_human_case_decision_report_addcreates or changes datadescribed as changing data
“Attach a structured analyst/MCP decision report to a notification/case without changing IP status or proposed action state.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
16 inputs, 3 required
- notificationIdstringrequired“Notification id from the case-action row.”
- decisionReportobject“Structured audit report explaining the decision, evidence reviewed, trace IDs, missing proof, and recommendations.”
- decisionSummarystring“Short decision summary to record on the IP/case history.”
- outcomestring“Decision outcome: blocked, rate_limited, false_positive, clean, deferred, case_action, rule_tuning, new_alert_rule, ambiguous, skipped, or other.”
- evidencearray“Evidence strings that support the decision.”
- reviewedHistoryarray“History/proofs reviewed before deciding.”
- traceIdsarray“Trace IDs reviewed for this decision.”
- pathsarray“Paths/endpoints reviewed for this decision.”
- ipsarray“IP addresses affected by this case-level decision report.”
- methodsarray“HTTP methods reviewed for this decision.”
- statusCodesarray“HTTP status codes reviewed for this decision.”
- userAgentsarray“User agents reviewed for this decision.”
- missingProofarray“Proof that was missing when the row is skipped or ambiguous.”
- recommendationsarray“Follow-up recommendations to record with the decision.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_ip_lookupreads or searches
“Look up SecureNow IP intelligence for an IP address.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
- ipstringrequired“IPv4 address.”
securenow_ip_tracesreads or searches
“Fetch traces associated with an IP address.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- ipstringrequired“IPv4 address.”
- appKeysstring or array“Application key or comma-separated/list of application keys.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
securenow_forensics_queryruns code or commandsdescribed as changing data
“Run a natural-language forensic query.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
6 inputs, 3 required
- querystringrequired“Natural-language forensic query.”
- applicationIdstring“Optional application database id.”
- instanceIdstring“Optional ClickHouse instance id.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_forensics_libraryreads or searches
“List saved forensics queries.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
securenow_analytics_summaryreads or searches
“Fetch response analytics summary.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input
- instanceIdstring“Optional ClickHouse instance id.”
securenow_automation_rules_listreads or searches
“List blocklist automation rules with app/environment scope and stats.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
securenow_automation_defaults_ensurecreates or changes datadescribed as changing data
“Create or refresh SecureNow default risk-score automation rules for the current account.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
3 inputs, 2 required
- forceEnableExistingboolean“Re-enable existing SecureNow default rules if the customer disabled them.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_automation_rule_getreads or searches
“Fetch one automation rule.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstringrequired“Automation rule id.”
securenow_automation_rule_createcreates or changes datadescribed as changing data
“Create a blocklist automation rule.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
12 inputs, 5 required
- namestringrequired“Rule name.”
- descriptionstring“Optional rule description.”
- conditionsarrayrequired“Condition array.”
- conditionLogicstring“AND or OR.”
- actionsarrayrequired“Action array, for example [{ "type":"addToBlocklist", "config":{ "reason":"...", "ttlHours":24 }}].”
- statusstring“Initial rule status: active or disabled.”
- applicationsAllboolean“Apply to all applications.”
- applicationKeysarray“Application keys when not applying to all applications.”
- environmentsAllboolean“Apply to all environments.”
- environmentsarray“Deployment environments when not applying to all environments.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_automation_rule_updatecreates or changes datadescribed as changing data
“Update a blocklist automation rule.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
13 inputs, 3 required
- idstringrequired“Automation rule id.”
- namestring“Rule name.”
- descriptionstring“Optional rule description.”
- statusstring“active or disabled.”
- conditionsarray“Condition array.”
- conditionLogicstring“AND or OR.”
- actionsarray“Action array.”
- applicationsAllboolean“Apply to all applications.”
- applicationKeysarray“Application keys when not applying to all applications.”
- environmentsAllboolean“Apply to all environments.”
- environmentsarray“Deployment environments when not applying to all environments.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_automation_rule_dry_runreads or searches
“Preview automation matches without writing blocklist entries.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- idstringrequired“Automation rule id.”
- limitnumber“Maximum notifications to scan.”
- sampleLimitnumber“Maximum sample matches to return.”
securenow_automation_rule_executeruns code or commandsdescribed as changing data
“Execute an automation rule and add matching IPs to the blocklist.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
3 inputs, 3 required
- idstringrequired“Automation rule id.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_automation_rule_deletedeletesdescribed as changing data
“Delete an automation rule.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
3 inputs, 3 required
- idstringrequired“Automation rule id.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_rate_limit_listreads or searches
“List rate-limit remediation rules with app/environment scope.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
- statusstring“Rule status: active, disabled, removed, or all.”
- searchstring“Optional IP/path/name search.”
- limitnumber“Maximum results to return.”
- pagenumber“Page number.”
- appKeystring“Optional application key scope.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
securenow_rate_limit_getreads or searches
“Fetch one rate-limit remediation rule.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstringrequired“Rate-limit rule id.”
securenow_rate_limit_testreads or searches
“Check whether an IP/path/method would match an active rate-limit rule.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs, 1 required
- ipstringrequired“IPv4 address to test.”
- pathstring“Request path to test.”
- methodstring“HTTP method to test.”
- appKeystring“Optional application key scope.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
securenow_rate_limit_removedeletesdescribed as changing data
“Remove a rate-limit remediation rule.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
3 inputs, 3 required
- idstringrequired“Rate-limit rule id.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_rate_limit_parse
“Use SecureNow AI to convert natural language into a rate-limit remediation draft without creating it.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 1 required
- textstringrequired“Natural-language rate-limit request, e.g.”
- draftobject“Optional existing draft fields to preserve or resolve phrases such as "this IP".”
securenow_rate_limit_create_from_textcreates or changes datadescribed as changing data
“Create a rate-limit remediation rule from natural language.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
4 inputs, 3 required
- textstringrequired“Natural-language rate-limit request.”
- draftobject“Optional existing draft fields or scope hints.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_rules_listreads or searches
“List alert rules, including system rules and app scope.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
securenow_alert_rule_getreads or searches
“Fetch one alert rule.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstringrequired“Alert rule id.”
securenow_alert_rule_versionsreads or searches
“List a rule's configuration version history (newest first).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
3 inputs, 1 required
- idstringrequired“Alert rule id.”
- limitnumber“Maximum results to return.”
- pagenumber“Page number.”
securenow_alert_rule_version_getreads or searches
“Fetch one version's full material snapshot (name/severity/mode/schedule/throttle/instant/exclusions and the resolved detection SQL) for diffing before a rollback.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- idstringrequired“Alert rule id.”
- versionnumberrequired“Version number to fetch.”
securenow_alert_rule_rollbackcreates or changes datadescribed as changing data
“Restore a prior version's full configuration onto a custom alert rule (re-validates the detection SQL first) and record it as a new version.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
4 inputs, 4 required
- idstringrequired“Alert rule id (must be a custom, non-system rule).”
- versionnumberrequired“Version number to restore.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_rule_updatecreates or changes datadescribed as changing data
“Update alert rule scope/status/schedule/throttle or record a review action.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
14 inputs, 3 required
- idstringrequired“Alert rule id.”
- namestring“Rule name for custom rules.”
- descriptionstring“Rule description for custom rules.”
- statusstring“Active, Disabled, or Paused.”
- applicationsAllboolean“Scope rule to all applications.”
- applicationsarray“Application keys when applicationsAll is false.”
- scheduleobject“Schedule patch.”
- throttleobject“Throttle patch.”
- alertChannelIdsarray“Alert channel ids.”
- reviewActionstring“Rule review action, e.g.”
- reviewNotestring“Review note.”
- reviewNotificationIdstring“Notification id tied to this review.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_rule_query_updatecreates or changes datadescribed as changing data
“Admin-only: update the shared public query mapping behind a system alert rule for all customer copies.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
9 inputs, 4 required
- idstringrequired“Alert rule id.”
- sqlQuerystringrequired“Full replacement SQL query.”
- expectedCurrentSqlHashstring“Optional SHA-256 hash of the current SQL to prevent stale overwrites.”
- applyGloballyboolean“Must be true.”
- reactivatePausedCopiesboolean“Whether to reactivate paused noisy copies after the query is tuned.”
- reviewNotificationIdstring“Optional notification id tied to this review/tuning action.”
- reviewNotestring“Optional review note.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_rule_instant_updatecreates or changes datadescribed as changing data
“Patch instant rule conditions/config with version/hash guards and before/after seeded tests.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
24 inputs, 5 required
- idstringrequired“Alert rule id.”
- operationsarray“Condition patch operations: add_condition, remove_condition, update_condition.”
- conditionsarray“Optional full replacement instant conditions array.”
- enabledboolean“Whether instant detection is enabled.”
- sourcestring“Instant event source.”
- matchModestring“Condition match mode: all or any.”
- blockboolean“Block the source IP when the instant conditions match.”
- blockTtlHoursnumber“How long an instant block lasts, in hours (default 1, max 168).”
- blockConditionsarray“Optional stricter conditions that must also match before blocking (same shape as conditions).”
- blockMatchModestring“Match mode for blockConditions: all or any (default any).”
- executionModestring“Rule execution mode: instant or hybrid when instant detection is enabled.”
- severitystring“Optional severity override: critical, high, medium, or low.”
- throttleobject“Throttle patch, for example { enabled:true, minutes:15 }.”
- expectedRuleVersionnumberrequired“Required current reviewState.reviewVersion from securenow_alert_rule_get.”
- expectedCurrentInstantHashstringrequired“Required SHA-256 hash of the current instant config from securenow_alert_rule_get.”
- expectedCurrentRuleHashstring“Optional SHA-256 hash of the current instant/throttle/severity surface from securenow_alert_rule_get.”
- applyGloballyboolean“Required true for system rules.”
- dryRunboolean“When true, validates and runs before/after seeded tests without saving.”
- reactivatePausedCopiesboolean“Whether to reactivate paused noisy copies after the instant rule is tuned.”
- fixturesarray“Optional seeded fixtures.”
- reviewNotificationIdstring“Optional notification id tied to this review/tuning action.”
- reviewNotestring“Optional review note.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_rule_conditions_getreads or searches
“Fetch instant rule conditions with rule version and hash guards for safe condition-level tuning.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstringrequired“Alert rule id.”
securenow_alert_rule_condition_updatecreates or changes datadescribed as changing data
“Patch instant alert-rule conditions with version/hash guards and seeded before/after tests.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
17 inputs, 5 required
- idstringrequired“Alert rule id.”
- operationsarray“Condition patch operations: add_condition, remove_condition, update_condition.”
- conditionsarray“Optional full replacement instant conditions array.”
- enabledboolean“Whether instant detection is enabled.”
- sourcestring“Instant event source.”
- matchModestring“Condition match mode: all or any.”
- executionModestring“Rule execution mode: instant or hybrid when instant detection is enabled.”
- expectedRuleVersionnumberrequired“Required current reviewState.reviewVersion from securenow_alert_rule_conditions_get.”
- expectedCurrentInstantHashstringrequired“Required SHA-256 hash of the current instant config from securenow_alert_rule_conditions_get.”
- expectedCurrentRuleHashstring“Optional SHA-256 hash of the current instant/throttle/severity surface from securenow_alert_rule_conditions_get.”
- applyGloballyboolean“Required true for system rules.”
- reactivatePausedCopiesboolean“Whether to reactivate paused noisy copies after the condition is tuned.”
- fixturesarray“Optional seeded fixtures.”
- reviewNotificationIdstring“Optional notification id tied to this review/tuning action.”
- reviewNotestring“Optional review note.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_rule_condition_candidate_testreads or searches
“Dry-run a condition-level instant-rule patch without saving it, including seeded benign/attack fixture checks.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
16 inputs, 5 required
- idstringrequired“Alert rule id.”
- operationsarray“Candidate condition operations to test.”
- conditionsarray“Optional full replacement instant conditions array to test.”
- enabledboolean“Whether instant detection would be enabled.”
- sourcestring“Instant event source.”
- matchModestring“Condition match mode: all or any.”
- executionModestring“Rule execution mode: instant or hybrid when instant detection is enabled.”
- expectedRuleVersionnumberrequired“Required current reviewState.reviewVersion from securenow_alert_rule_conditions_get.”
- expectedCurrentInstantHashstringrequired“Required SHA-256 hash of the current instant config from securenow_alert_rule_conditions_get.”
- expectedCurrentRuleHashstring“Optional SHA-256 hash of the current instant/throttle/severity surface from securenow_alert_rule_conditions_get.”
- applyGloballyboolean“Required true for system rules, even for admin dry-runs.”
- fixturesarray“Optional seeded fixtures.”
- reviewNotificationIdstring“Optional notification id tied to this review/tuning action.”
- reviewNotestring“Optional review note.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_rule_condition_diffreads or searches
“Return the current instant conditions, candidate conditions, hashes, and before/after fixture behavior without saving.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
14 inputs, 5 required
- idstringrequired“Alert rule id.”
- operationsarray“Candidate condition operations to diff.”
- conditionsarray“Optional full replacement instant conditions array to diff.”
- enabledboolean“Whether instant detection would be enabled.”
- sourcestring“Instant event source.”
- matchModestring“Condition match mode: all or any.”
- executionModestring“Rule execution mode: instant or hybrid when instant detection is enabled.”
- expectedRuleVersionnumberrequired“Required current reviewState.reviewVersion from securenow_alert_rule_conditions_get.”
- expectedCurrentInstantHashstringrequired“Required SHA-256 hash of the current instant config from securenow_alert_rule_conditions_get.”
- expectedCurrentRuleHashstring“Optional SHA-256 hash of the current instant/throttle/severity surface from securenow_alert_rule_conditions_get.”
- applyGloballyboolean“Required true for system rules, even for admin dry-runs.”
- fixturesarray“Optional seeded fixtures used to explain benign removals and attack coverage.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_rule_testruns code or commandsdescribed as changing data
“Start an alert rule test.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 3 required
- idstringrequired“Alert rule id.”
- applicationKeystring“Application key to test.”
- modestring“dry_run (read-only, recommended) or live (inserts synthetic spans).”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_rule_candidate_testruns code or commands
“Dry-run a candidate SQL/query guard for an alert rule without saving it.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
5 inputs, 4 required
- idstringrequired“Alert rule id.”
- applicationKeystring“Application key to test.”
- candidateSqlQuerystringrequired“Full candidate SQL query to dry-run without saving.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_alert_rule_test_resultreads or searches
“Poll alert rule test status and results.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs, 2 required
- idstringrequired“Alert rule id.”
- testIdstringrequired“Alert rule test id.”
securenow_alert_rule_exclusions_listreads or searches
“List exclusions embedded on one alert rule.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
1 input, 1 required
- idstringrequired“Alert rule id.”
securenow_alert_rule_exclusion_addcreates or changes datadescribed as changing data
“Add a restrictive exclusion to one alert rule.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
7 inputs, 3 required
- idstringrequired“Alert rule id.”
- conditionsarray“Restrictive exclusion conditions.”
- matchModestring“all or any.”
- reasonstringrequired“Short human-readable reason for the write action.”
- pathPatternstring“Optional path pattern.”
- isActiveboolean“Whether the exclusion is active.”
- confirmbooleanrequired“Required for write actions.”
securenow_alert_rule_exclusion_removedeletesdescribed as changing data
“Remove an alert rule exclusion.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
4 inputs, 4 required
- idstringrequired“Alert rule id.”
- exclusionIdstringrequired“Exclusion id.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_blocklist_listreads or searches
“List blocked IPs.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
8 inputs
- limitnumber“Maximum results to return.”
- pagenumber“Page number.”
- statusstring“Block entry status: active or removed.”
- approvalStatusstring“Optional approval filter: pending, approved, or rejected.”
- searchstring“Optional IP prefix search.”
- viewstring“List view: all or operational.”
- appKeystring“Optional application key scope.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
securenow_blocklist_pending_listreads or searches
“List legacy or AI-prepared blocklist entries with approvalStatus=pending.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
- limitnumber“Maximum results to return.”
- pagenumber“Page number.”
- searchstring“Optional IP prefix search.”
- appKeystring“Optional application key scope.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
securenow_blocklist_pending_approvecreates or changes datadescribed as changing data
“Approve one pending blocklist entry so the firewall enforces it.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
3 inputs, 3 required
- idstringrequired“Pending blocklist entry id.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_blocklist_pending_rejectdeletesdescribed as changing data
“Reject one pending blocklist entry and remove it from enforcement consideration.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
3 inputs, 3 required
- idstringrequired“Pending blocklist entry id.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_blocklist_pending_bulk_approvecreates or changes datadescribed as changing data
“Approve multiple pending blocklist entries after they have all been reviewed under the same safe policy.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
3 inputs, 3 required
- idsarrayrequired“Pending blocklist entry ids to approve.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_blocklist_pending_bulk_rejectdeletesdescribed as changing data
“Reject multiple pending blocklist entries after they have all been reviewed as false positives or stale/ambiguous.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
3 inputs, 3 required
- idsarrayrequired“Pending blocklist entry ids to reject.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_blocklist_addcreates or changes datadescribed as changing data
“Add an IP/CIDR to the blocklist, optionally scoped to a route/method.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
10 inputs, 3 required
- ipstringrequired“IPv4 address or CIDR.”
- reasonstringrequired“Short human-readable reason for the write action.”
- expiresAtstring“Optional expiry time as ISO 8601.”
- metadataobject“Optional metadata.”
- appKeystring“Optional application key to scope this block.”
- pathPatternstring“Optional route/path pattern, for example /admin*.”
- pathMatchModestring“Path matching mode.”
- methodstring“HTTP method scope.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
- confirmbooleanrequired“Required for write actions.”
securenow_blocklist_removedeletesdescribed as changing data
“Compatibility alias for unblocking a blocklist entry while retaining block report/history.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
3 inputs, 3 required
- idstringrequired“Blocklist entry id.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_blocklist_unblockdeletesdescribed as changing data
“Unblock a blocklist entry so firewall enforcement stops, while retaining the block report, history, and unblock audit trail.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
3 inputs, 3 required
- idstringrequired“Blocklist entry id.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_blocklist_statsreads or searches
“Return blocklist statistics.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
Takes no inputs.
securenow_allowlist_listreads or searches
“List restrictive allowlist entries.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
- limitnumber“Maximum results to return.”
- pagenumber“Page number.”
- appKeystring“Optional application key scope.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
securenow_allowlist_addcreates or changes datadescribed as changing data
“Dangerous production action: add an IP/CIDR to the restrictive allowlist.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
9 inputs, 4 required
- ipstringrequired“IPv4 address or CIDR.”
- labelstring“Human-readable label.”
- reasonstringrequired“Short human-readable reason for the write action.”
- expiresAtstring“Optional expiry time as ISO 8601.”
- applicationsAllboolean“Apply to all applications.”
- applicationKeysarray“Application keys to scope this allowlist entry to.”
- allowlistDenyAllApprovedbooleanrequired“Must be true only after the user explicitly approves deny-by-default allowlist behavior.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
- confirmbooleanrequired“Required for write actions.”
securenow_allowlist_removedeletesdescribed as changing data
“Remove an allowlist entry.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
3 inputs, 3 required
- idstringrequired“Allowlist entry id.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_trusted_listreads or searches
“List trusted IPs.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
2 inputs
- appKeystring“Optional application key scope.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
securenow_trusted_addcreates or changes datadescribed as changing data
“Add a trusted IP/CIDR for known-safe infrastructure, monitors, office/VPN traffic, or scoped false-positive suppression.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
8 inputs, 3 required
- ipstringrequired“IPv4 address or CIDR.”
- labelstring“Human-readable label.”
- notestring“Optional note.”
- applicationsAllboolean“Apply to all applications.”
- applicationKeysarray“Application keys to scope this trusted IP to.”
- environmentstring“Deployment environment scope: production, staging, preview, local, test, or all.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”
securenow_trusted_removedeletesdescribed as changing data
“Remove a trusted IP entry.”
Publisher declares: read-only no · destructive yes · idempotent no · open-world no
3 inputs, 3 required
- idstringrequired“Trusted IP entry id.”
- confirmbooleanrequired“Required for write actions.”
- reasonstringrequired“Short human-readable reason for the write action.”

Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-10-23.

How well are its tools described?

Features #4 and #5

How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.

Descriptions

AI reading of each description

Says what the tool does: 100% of 90 tools
Says what it returns: 65% of 69 tools
States limits, defaults or errors: 15% of 84 tools
Says when to use it: 2% of 90 tools
Items covered per tool: 1.7 of 4 on average

Counted from the listing

Parameters with a description: 100% of 551
Tools with a description: 100% of 90
Typical description length: 99 characters

The tool set

Counted from the listing

Tools: 90
Size of the list: about 24,234 tokens for an agent to load (characters ÷ 4)
Naming: 90 of 90 names use snake_case

AI reading: easy to mix up

securenow_blocklist_remove and securenow_blocklist_unblock
securenow_blocklist_remove and securenow_allowlist_remove
securenow_blocklist_unblock and securenow_allowlist_remove

The AI items cover 90 of 90 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found these, comparing tools within groups of 40. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.

How do I add it to my client?

Config from the registry entry

From the npm package securenow

Our sandbox started this package on 2026-10-23 (a read-only session: no tool was called).

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below. The command runs the publisher’s code on your machine.

Claude Desktop · claude_desktop_config.json (Settings → Developer → Edit Config)

{
  "mcpServers": {
    "securenow": {
      "command": "npx",
      "args": [
        "-y",
        "securenow@8.12.4",
        "mcp"
      ]
    }
  }
}

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "securenow": {
      "command": "npx",
      "args": [
        "-y",
        "securenow@8.12.4",
        "mcp"
      ]
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "securenow": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "securenow@8.12.4",
        "mcp"
      ]
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"securenow","type":"stdio","command":"npx","args":["-y","securenow@8.12.4","mcp"]}'

Claude Code

claude mcp add --transport stdio securenow -- npx -y securenow@8.12.4 mcp

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 -- npx -y securenow@8.12.4 mcp

Arguments are written as the registry entry gives them; a named one as “--name value”, the form the registry documentation shows.
This runs the publisher's code on your machine (npx). Read its README first.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

From the remote endpoint (Streamable HTTP)

Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.

Claude Desktop or claude.ai

Settings → Connectors → Add custom connector, then paste:
https://api.securenow.ai/mcp

Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json

{
  "mcpServers": {
    "securenow": {
      "url": "https://api.securenow.ai/mcp"
    }
  }
}

VS Code · .vscode/mcp.json

{
  "servers": {
    "securenow": {
      "type": "http",
      "url": "https://api.securenow.ai/mcp"
    }
  }
}

VS Code (command line) · Bash or zsh terminal (macOS, Linux)

code --add-mcp '{"name":"securenow","type":"http","url":"https://api.securenow.ai/mcp"}'

Claude Code

claude mcp add --transport http securenow https://api.securenow.ai/mcp

Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+

npx @modelcontextprotocol/inspector@2.11.0 --server-url https://api.securenow.ai/mcp --transport http

The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.

Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.

Can it be installed, and is it up to date?

Version pin · advisories

Listed version

Registry lists: 8.12.4
Latest stable: 8.12.4
Status: current
Withdrawn: no

Source: registry.npmjs.org · 2026-10-23. About the version the registry lists; a manual install may resolve to a different one.

Dependency advisories

Counted in the full dependency tree as resolved on 2026-10-24 (npm audit; each bar counts packages with an advisory, not advisories). Bars share one scale. The package itself has no known vulnerability (OSV.dev).

Integrity, provenance, license

Integrity: sha512-UP0MhsWnIz7ISPB0U…
Signature: signed
License: ISC

Source: the package registry · 2026-10-22.

Usage

Downloads: 1,629 in the last month

Source: api.npmjs.org · 2026-10-22.

Does the registry listing match what we found?

Feature #6

The registry verifies a package once, when it is published, and does not re-check it. A difference below is about the listing, not a judgement of the publisher.

Registry says	We found	Result	Source · date
Remote endpoint api.securenow.ai/mcp	Endpoint answered and asked for sign-in	matches	our test · 2026-10-23
No credential declared as required	Required sign-in	differs	our test · 2026-10-23
Published package can be started	Started and answered	matches	our test · 2026-10-23
Version 8.12.4 on npm	Exists and can be installed	matches	npm · 2026-10-23
Repository github.com/securenow-ai/securenow-npm	Opens publicly	matches	api.github.com · 2026-10-22

Who made it?

Feature #7 · lineage

Facts about the publisher. We do not turn them into a trust score.

Namespace: ai.securenow
GitHub owner: an organization (securenow-ai)
Build record: signed

Repository: github.com/securenow-ai/securenow-npm
Stars: 0
Repository age: 181–365 days
Last push: 181–365 days ago
Archived: no
Security policy: none found (we looked for SECURITY.md in the repository and in its owner’s .github repository)

Source: the registry entry and api.github.com · 2026-10-22; security policy read from GitHub · 2026-10-23.

Publish this server? Run these checks against it yourself before release, from your own machine: a server the command starts, or your own server at its URL after a one-time proof that you control it: npx protocolprobe-selftest.

Choosing

Record checks

Public records · not a safety rating

6 of 9 record checks met

#1,418 of 15,115 packages by monthly downloads, tied with 1 other
Not ranked by stars: 0 stars (ranked from 10)

MetRegistry entry is active and says how to run itActive, with a package or a remote address.
MetSource repository link opensThe linked GitHub repository is public.
MetRepository is not archivedNot archived.
Not metCode pushed to the repository in the 90 days before our checkLast push 181-365 days before our check.
Not metRepository publishes a security policy (SECURITY.md)No SECURITY.md in the places GitHub reads it from.
MetPackage names its licence with a standard (SPDX) identifierISC
MetThe version the registry lists can be installed and is not withdrawnThe listed version exists and is current.
Not metnpm package carries build provenance (attestation)Signed by npm, but no build attestation.
MetNo known critical or high advisory in the package or its dependenciesNone known in the package or its dependency tree.

Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-22. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating. How each check works · Leaderboards

Common questions about ai.securenow/securenow

Answered from the data above

Is ai.securenow/securenow safe to install?

We do not rate servers as safe or unsafe. 6 of its 9 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. The listed version is the latest stable release. The package itself has no known vulnerability (OSV.dev). Its full dependency tree has no known advisory. 43 of its tools describe changing data (our AI model's reading of the descriptions). These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.

Has ai.securenow/securenow been security tested?

Partly. 4 of the 13 checks that apply to it were exercised. We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security verdict is published before verification.

What can ai.securenow/securenow do?

It lists 90 tools. In our AI model's reading of their descriptions (two runs had to agree, nobody checked it by hand), they include tools that read or search, create or change data, delete and run code or commands. We did not call any tool, so this describes the text, not the behaviour.

Can ai.securenow/securenow change or delete data?

43 of its tools say in their description that they create, edit, delete, send or run something (our AI model's reading). We did not call any tool, so we cannot say what actually happens.

Does ai.securenow/securenow publish a security policy?

We found no SECURITY.md in its repository (root, .github/ or docs/) or in its owner's .github repository.

Is the listed version current?

Yes. The registry lists 8.12.4, the latest stable release on npm.

Where is the source code of ai.securenow/securenow?

In github.com/securenow-ai/securenow-npm, which opens publicly.

Found this page useful?

Anonymous · no sign-in

A quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.

Similar servers

Same topic · AI-read

io.github.ashlrai/phantom-secrets-mcpPhantom Secretsalso has tools that creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.maximilianfeix/hexverohexveroalso has tools that creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.agent-passport-system/agent-passport-mcpAgent Passport System — Cryptographic Identity for AI Agentsalso has tools that creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.vmware-skills/vmware-nsx-securityVMware NSX Securityalso has tools that creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.sparkvibe-io/GuardianShieldalso has tools that creates or changes data, deletes, runs code or commands, reads or searchescompare with this one
io.github.lutfizp/keelKeelalso has tools that creates or changes data, deletes, runs code or commands, reads or searchescompare with this one

Active servers whose topic is also “security” and that have at least one tool of the same kind; most kinds in common first, then most GitHub stars. The topic and the tool kinds are an AI model's reading of the publishers' descriptions, not checked by hand. Similar is not a recommendation.

Compare with another server

Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.

Security testing

What did we test, and what did we leave out?

18 checks · features #1, #2

Not probed (read-only run)

We started the package in an isolated sandbox and read what it declares, but this test round was read-only, so its tools were not called. No security score is given; a check we did not run is never counted as passed.

The 18 checks at a glanceour test · 2026-10-23

Inventory: exercised
Hidden instructions: exercised
Real execution: not run · our policy
Secret leak: not run · nothing to check it against
Internal addresses: not run · our policy
Unconfirmed changes: not run · our policy
Bad input: not run · our policy
Model requests: not run · nothing to check it against
Sensitive questions: not run · nothing to check it against
Folder boundary: not run · our policy
Log leaks: not run · nothing to check it against
Hidden content: exercised
Fake assistant turns: exercised
Token passthrough: not applicable
Token audience: not applicable
Sign-in redirect: not applicable
Consent handling: not applicable
Sign-in metadata: not applicable

4 exercised9 not run (reason given)5 not applicable

Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 4 of the 13 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.

Exercised · 4

1Inventory
tool-listReads the declared tools, resources and prompts.exercised
2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
12Hidden content
audience-hidingChecks resources that hide content from the user.exercised
13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.exercised

Not run, with the reason · 9

3Real execution
real-executionCalls a tool and checks what really happens.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against
10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the package's tools. This test round was read-only, so no tool was called; tools can act on outside services with the publisher's or a user's account.not run · our policy
11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against

Does not apply to this server · 5

14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
17Consent handling
confused-deputyChecks consent handling when one service acts for another.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable
18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.The server runs locally over standard input/output, so there is no sign-in flow to check.not applicable

Source: our own test in an isolated sandbox, 2026-10-23, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model. This server also has a remote test (1 of 18 applicable checks exercised).

What happened during the test?

Feature #8

The steps in order, as the test record holds them.

0 msStarted the published package in an isolated sandbox (read-only mode)
12,328 msConnected after 0 redirects.
Read the inventory: 90 tools, 5 resources, 9 prompts.
14,643 msFinished: 4 checks exercised.

Reference

How is it classified?

18 fields

One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.

TopicAI-classified

security

AI-classified · 2026-10-23

Pricing modelAI-classified

no value

No value: the AI answer was held back because the quoted text did not clearly support it.

Programming language

JavaScript

api.github.com · 2026-10-23

Hosting type

remote and local package

registry · 2026-10-23

MCP capability

prompts, resources, tools

our test · 2026-10-23

Transport

standard input/output, streamable HTTP

registry · 2026-10-23

Required credentials

none declared

registry · no declaration is not a guarantee

Package registry

npm

registry · 2026-10-23

Freshness

0–30 days

registry updatedAt · 2026-10-23

Lifecycle status

active

registry · 2026-10-23

License class

permissive

package registry · 2026-10-22

Integrity hash

declared (sri)

package registry · 2026-10-22

Signature / provenance

signed

package registry · 2026-10-22

Dependency advisories

none known

npm audit · 2026-10-24

Popularity

1,629 downloads a month

package registry · 2026-10-22

Publisher signals

owner: an organization · repository age: 181–365 days · stars: 0–9 · build record: signed

api.github.com · 2026-10-22

Maintenance

slowing (no push for a while)

api.github.com · 2026-10-22

Environment

either (remote or your machine)

where it runs, from the hosting type

“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.

Cite or correct this page

Sources and corrections

Suggested citation

ProtocolProbe. “ai.securenow/securenow: MCP server record.” Data checked 2026-10-23. https://protocolprobe.com/mcp/servers/ai.securenow/securenow

Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.

As JSON: this record in the API · API documentation.

Badge for your README

[![ProtocolProbe](https://protocolprobe.com/api/v1/badge/ai.securenow/securenow)](https://protocolprobe.com/mcp/servers/ai.securenow/securenow)

It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.

Something wrong, or is this yours?

If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.

Write to hello@protocolprobe.com · corrections log · methodology