MCP servers › io.github.revclamp › revclamp-mcp
MCP server · registry snapshot 2026-10-26 · last tested 2026-10-26
io.github.revclamp/revclamp-mcp
RevClamp MCP Server — the publisher's title
by revclamp · GitHub account (the registry's namespace rule)repository: same ownerSource ↗
Zero-take-rate Stripe 2025-03-31.basil, Visa CE 3.0 & EU/UK VIES VAT guardrails MCP server. — the publisher's description
Summary
io.github.revclamp/revclamp-mcp is a remote MCP server listed in the official MCP registry at version 1.20.7, under the namespace of the GitHub account revclamp. Its linked repository, github.com/revclamp/revclamp-mcp, belongs to the same GitHub account. On 2026-10-26 ProtocolProbe connected to it in read-only mode and read its inventory: 9 tools, 0 resources and 0 prompts.
Record checks
4 of 4 record checks met · 4 do not apply · 1 not checked
- met: Registry entry is active and says how to run it
- met: Source repository link opens
- met: Repository is not archived
- met: Code pushed to the repository in the 90 days before our check
- not checked: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- 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?
Operate this server? Correct a fact · README badge · Run the checks yourself
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Repository
- public
- Tools
- 9
- Last tested
- 2026-10-26
Tool list size
10,248 tokens on Claude Opus 5.5
Added to every request that loads this server's tools (9 tools). Counted with Anthropic's token counter on 2026-10-26, from the tool list we read on 2026-10-26. Median across 23,424 counted servers: 2,725 tokens. How it is counted
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-10-26 (api.revclamp.com), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (1.20.7).
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-10-26
- Mode
- read-only (no tool calls)
- Latest version
- 1.20.7, published 2026-10-26 (registry, as of the 2026-10-26 snapshot)
- First listed version
- 2026-10-25 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 3 versions listed, 2026-10-25 to 2026-10-26; 3 in the 90 days before the 2026-10-26 snapshot.(versions still listed in the registry only)
Most recent 3 versions
1.20.7· 2026-10-261.20.6· 2026-10-251.20.0· 2026-10-25
- Registry data
- snapshot 2026-10-26
- Package and repository
- checked 2026-10-26
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry; repository link does not open; repository archived; no push in over 365 days. Does not apply: listed version cannot be installed or is withdrawn. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
New in the registry: not in the list of 2026-10-24, listed on 2026-10-26 with version 1.20.7 (published 2026-10-26).
Source: the official MCP Registry list on 2026-10-24 and on 2026-10-26.
What it is
What does this server offer?
Observed inventoryNone of its 9 tools are described as changing anything. For 9 the reading was uncertain, so no mark is shown.
- revclamp_audit_revenue_leakage
“Run a deterministic 90-day B2B revenue leakage and chargeback readiness audit across Stripe subscriptions, AI/API usage telemetry events, and open disputes.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
dunningGracePeriodDaysinteger“Custom dunning grace window in integer days (valid range: 0 to 14, default: 3) allowed after latest_invoice_failed_at before flagging past_due subscriptions as…”costPerEventCentsinteger“Estimated marginal compute or API cost per leaked usage event in integer USD cents (valid range: 1 to 100000, default: 142 i.e.”customersarray“Optional array of up to 50 Stripe customer snapshots (each with id like 'cus_123', optional email, subscriptions array or list object, and subscriptionsHasMore…”usageEventsarray“Optional array of up to 200 product/AI API usage telemetry events (each with stripe_customer_id or email, event_name, and occurredAtSec Unix timestamp in secon…”disputesarray“Optional array of up to 50 Stripe dispute objects (each with id like 'du_123', customer, amount in cents, reason such as 'fraudulent', and status such as 'need…”demoboolean“Optional simulation flag (boolean) for deterministic sample audit preview.”
- revclamp_evaluate_ghost_usage
“Evaluate whether a specific customer's AI or API usage event constitutes unpaid ghost usage across multi-subscription Stripe 2025-03-31.basil state, enforcing fail-closed pagination (has_more must be…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
8 inputs, 1 required
customerIdstring“Stripe customer identifier to evaluate (format example: 'cus_9s6XKzkNRiz8i3', max 64 chars).”subscriptionsrequired“Required Stripe customer subscriptions payload: either a Stripe list object ({ data: [...], has_more: false }) or a raw array of up to 50 subscription objects …”usageEventobject“Optional metered usage event object containing customer_id (or stripe_customer_id), event_name, and occurred_at (or occurred_at_sec).”subscriptionsHasMoreboolean“Pagination completeness flag (boolean).”dunningGracePeriodDaysinteger“Dunning grace window in integer days (valid range: 0 to 14, default: 3) after latest_invoice_failed_at during which past_due subscriptions remain entitled.”usageTimestampSecinteger“Optional Unix epoch timestamp in integer seconds (e.g.”occurredAtSecinteger“Optional alias for usageTimestampSec: Unix epoch timestamp in integer seconds (e.g.”demoboolean“Optional simulation flag (boolean) for deterministic ghost-usage preview.”
- revclamp_stage_stripe_dispute_ce3
“Evaluate Visa Compelling Evidence 3.0 (CE 3.0) qualification across 120-to-365-day historical charges (requiring at least 2 settled, non-refunded, non-disputed prior transactions sharing IP address, …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
9 inputs
disputeIdstring“Stripe dispute identifier being staged (format example: 'du_1QxyzEnterpriseDispute01', default: 'du_mcp_staged_01', max 64 chars).”customerIdstring“Stripe customer identifier associated with the disputed charge (format example: 'cus_enterprise_88', default: 'cus_mcp_enterprise_01', max 64 chars).”disputeReasonstring“Stripe dispute reason code (e.g.”existingUncategorizedTextstring“Optional existing merchant evidence notes in Stripe evidence.uncategorized_text or access_activity_log (up to 18,000 chars) to preserve via append-only merge w…”existingAccessActivityLogstring“Optional alias for existingUncategorizedText: existing merchant evidence notes in Stripe evidence.access_activity_log (up to 18,000 chars) to preserve via appe…”disputedTransactionobject“Optional disputed charge snapshot object containing id (e.g.”priorTransactionsarray“Optional array of up to 1000 historical Stripe charge objects (each with id, status: 'succeeded', disputed: false, refunded: false, occurredAtSec 120-365 days …”usageEventsarray“Optional array of up to 200 customer product/API usage telemetry events (each with occurredAtSec Unix seconds, stripe_customer_id, and event_name) for append-o…”demoboolean“Optional simulation flag (boolean) to stage a labeled sample dispute preview.”
- revclamp_validate_eu_vat_vies
“Normalize EU-27 and Northern Ireland (XI) B2B VAT identifiers (including mandatory Greece ISO-3166 GR to EL prefix normalization) and evaluate cross-border 0% VAT reverse-charge eligibility, VIES con…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
5 inputs, 1 required
sellerCountrystring“Two-letter EU-27 or XI member state prefix of the merchant's dispatch warehouse (e.g.”buyerVatIdstringrequired“Required buyer EU or Northern Ireland VAT registration number to normalize and validate (e.g.”viesModestring“VIES evaluation mode: 'FORMAT_ONLY' (deterministic EU/XI syntax validation without consultation), 'VALID' (deterministic active VAT simulation, default), 'INVA…”consultationNumberstring“Optional VIES requester consultation reference number (e.g.”demoboolean“Optional simulation flag (boolean) for deterministic VIES gateway preset evaluation.”
- revclamp_reconcile_b2b_net_terms
“Reconcile B2B wholesale Net-15, Net-30, and Net-60 invoice deposits, partial payments, and credit notes using exact integer minor-unit (EUR/USD cent) arithmetic with zero IEEE-754 floating-point drif…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
12 inputs, 1 required
orderIdstring“B2B wholesale order or invoice identifier (e.g.”totalOrderCentsinteger“Gross invoice total in positive integer minor currency units / cents (e.g.”orderTotalCentsinteger“Alias for totalOrderCents: gross invoice total in positive integer minor currency units / cents (must be > 0).”paidAmountCentsintegerrequired“Required cumulative amount collected from the buyer in non-negative integer cents (e.g.”creditNoteCentsinteger“Optional post-invoice credit notes or return adjustments in integer cents (valid range: 0 to totalOrderCents, default: 0; singular alias for creditNotesCents).”creditNotesCentsinteger“Optional post-invoice credit notes or return adjustments in integer cents (valid range: 0 to totalOrderCents, default: 0; plural alias for creditNoteCents).”requiredDepositCentsinteger“Optional explicit upfront deposit threshold in integer cents (valid range: 0 to effectiveTotalCents).”requiredDepositPercentinteger“Optional upfront deposit percentage required before releasing warehouse fulfillment hold (valid range: 0 to 100, default: 30 i.e.”paymentTermsDaysinteger“Optional B2B net payment terms maturity window in integer days (allowed values: 15, 30, or 60 for Net-15, Net-30, or Net-60; default: 30).”daysElapsedSinceInvoiceinteger“Optional elapsed integer days since invoice issuance (valid range: 0 to 3650, default: 5).”toleranceCentsinteger“Optional rounding/FX reconciliation tolerance in integer cents (valid range: 0 to min(500, 1% of totalOrderCents), default: 0).”demoboolean“Optional sandbox flag (boolean).”
- revclamp_verify_webhook_signature
“Generate and verify canonical Stripe-Signature (t=<unix>,v1=<hex_sha256>), X-Shopify-Hmac-Sha256 (<base64_sha256>), and X-RevClamp-Signature (t=<unix>,v1=<hex_sha256>) headers over exact UTF-8 webhoo…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
7 inputs
providerstring“Webhook signature provider scheme to evaluate: 'stripe' (Stripe-Signature t=<sec>,v1=<hex>, default), 'shopify' (X-Shopify-Hmac-Sha256 Base64 raw UTF-8 HMAC), …”secretstring“Synthetic or test webhook signing secret (default: 'whsec_test_revclamp_sandbox_secret_2026', max 256 chars).”rawPayloadstring“Exact unparsed UTF-8 webhook request body string (up to 16,384 chars) used to compute the canonical SHA-256 HMAC digest.”timestampSecinteger“Optional Unix epoch timestamp in integer seconds (valid range: 1 to 9999999999; defaults to current server Unix timestamp) used when generating or verifying ti…”signatureHeaderstring“Optional supplied HTTP signature header value to verify via crypto.timingSafeEqual (e.g.”toleranceSecinteger“Optional replay window tolerance in integer seconds (valid range: 1 to 3600, default: 300).”demoboolean“Optional sandbox flag; uses synthetic defaults when provider, secret, or rawPayload are omitted.”
- revclamp_calculate_roi_and_plan_fit
“Deterministically calculate monthly and annual B2B margin savings using exact integer USD cents when replacing a 25%-30% contingency chargeback agency with RevClamp flat-rate 0% commission plans ($19…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
4 inputs
monthlyWonDisputeUsdnumber“Monthly won Stripe chargeback volume in USD (valid range: 0 to 10000000, default: 10000) subject to legacy agency take-rate fees.”monthlyGhostBleedUsdnumber“Monthly unpaid AI/API or SaaS usage bleed stopped by RevClamp basil entitlement guards in USD (valid range: 0 to 10000000, default: 600).”contingencyTakeRatePercentnumber“Competitor chargeback agency contingency commission percentage (valid range: 1 to 50, default: 25 for 25% take-rate tools).”monthlyUsageEventsinteger“Monthly verified usage events across your workspace (integer 0 to 50000000, default: 250000) used to recommend Starter (<=100k), Growth (<=1M), or Scale (<=5M).”
- revclamp_simulate_webhook_replay
“Deterministically evaluate an ordered or out-of-order sequence of 1-10 Stripe/Shopify/RevClamp subscription lifecycle webhooks against a 72-hour idempotency deduplication Set (eventId), a configurabl…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
5 inputs
scenarioPresetstring“Scenario preset to evaluate when custom events are omitted (default: 'out_of_order_stale_update_after_cancel').”eventsarray“Optional custom array of 1 to 10 webhook events ({ eventId, eventType, createdSec, subscriptionStatus, tier, currentPeriodEndSec }) in arrival order.”nowSecinteger“Reference evaluation timestamp in Unix seconds used to check the 72-hour idempotency window.”idempotencyWindowSecinteger“Deduplication and replay-acceptance window in seconds (valid range: 60 to 2592000, default: 259200 for 72 hours).”demoboolean“Optional sandbox flag to run the preset replay simulation.”
- revclamp_lint_dispute_evidence
“Deterministically lint a Stripe dispute evidence[access_activity_log] payload against Stripe's 18,000 UTF-16 code unit (String.prototype.length) ceiling, UTF-8 byte length, non-destructive --- BEGIN …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world no
6 inputs
presetstring“Scenario preset to evaluate when custom evidenceLogText is omitted (default: 'valid_ce3_non_destructive').”existingMerchantNotesstring“Existing human AE/support notes inside evidence[access_activity_log] that must be preserved.”evidenceLogTextstring“Merged or candidate Stripe dispute evidence[access_activity_log] payload evaluated against the 18,000 UTF-16 code unit ceiling and non-destructive delimiter ma…”priorMatchedCountinteger“Number of prior undisputed Stripe charges (120d-365d old) with matching customer_id and IP/device fingerprint (Visa CE 3.0 requires >= 2).”hasIpMatchboolean“Whether the disputed charge IPv4/IPv6 address matches the historical undisputed charges.”hasDeviceMatchboolean“Whether the disputed charge device_id fingerprint matches the historical undisputed charges.”
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 2026-10-26.
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
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 100% of 62
- Tools with a description
- 100% of 9
- Typical description length
- 731 characters
The tool set
Counted from the listing
- Tools
- 9
- Size of the list
- about 6,346 tokens for an agent to load (characters ÷ 4)
- Naming
- 9 of 9 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 9 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 none. 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 remote endpoint (Streamable HTTP)
We connected to this URL on 2026-10-26 (a read-only session: no tool was called).
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.revclamp.com/api/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"revclamp-mcp": {
"url": "https://api.revclamp.com/api/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"revclamp-mcp": {
"type": "http",
"url": "https://api.revclamp.com/api/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"revclamp-mcp","type":"http","url":"https://api.revclamp.com/api/mcp"}'Claude Code
claude mcp add --transport http revclamp-mcp https://api.revclamp.com/api/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"revclamp-mcp": {
"type": "streamableHttp",
"url": "https://api.revclamp.com/api/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"revclamp-mcp": {
"httpUrl": "https://api.revclamp.com/api/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.revclamp-mcp] url = "https://api.revclamp.com/api/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"revclamp-mcp": {
"url": "https://api.revclamp.com/api/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.revclamp.com/api/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- 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; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). 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.
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint api.revclamp.com/api/mcp | Session opened | matches | our test · 2026-10-26 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-10-26 |
| Repository github.com/revclamp/revclamp-mcp | Opens publicly | matches | api.github.com · 2026-10-26 |
Who made it?
Feature #7 · lineage
Facts about the publisher. We do not turn them into a trust score.
- Namespace
- io.github.revclamp
- GitHub owner
- a personal account (revclamp)
- Repository
- github.com/revclamp/revclamp-mcp
- Stars
- 0
- Repository age
- 0–30 days
- Last push
- 0–30 days ago
- Archived
- no
Source: the registry entry and api.github.com · 2026-10-26.
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 rating4 of 4 record checks met · 4 do not apply · 1 not checked
- Not ranked by downloads: a remote server publishes no download figure
- 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.
- MetCode pushed to the repository in the 90 days before our checkLast push 0-30 days before our check.
- Not checkedRepository publishes a security policy (SECURITY.md)We did not read this repository's security policy.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-10-26. 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 io.github.revclamp/revclamp-mcp
Answered from the data aboveWho publishes io.github.revclamp/revclamp-mcp?
The registry ties the namespace io.github.revclamp to the GitHub account revclamp; only its owner can publish under it. Its linked repository, github.com/revclamp/revclamp-mcp, belongs to the same GitHub account. These are facts from the registry and GitHub, not a rating.
Is io.github.revclamp/revclamp-mcp safe to install?
We do not rate servers as safe or unsafe. 4 of its 4 applicable record checks are met (facts from public records, each listed on this page). What the records show: Its source repository opens publicly. Its repository had a push in the last 90 days. These are facts with their sources on this page, not a safety guarantee, and we did not run its tools.
Does io.github.revclamp/revclamp-mcp need an API key or sign-in?
It opened a session without any credential on 2026-10-26. The registry entry declares no required credential; no declaration is not a guarantee.
Has io.github.revclamp/revclamp-mcp been security tested?
Partly. 2 of the 14 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security verdict is published before verification.
Where is the source code of io.github.revclamp/revclamp-mcp?
In github.com/revclamp/revclamp-mcp, which opens publicly.
Found this page useful?
Anonymous · no sign-inA 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.
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 (we call no server's tools)
We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.
- 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: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: not applicable
2 exercised12 not run (reason given)4 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 2 of the 14 checks that apply to it were exercised. We do not publish security-check outcomes for named servers.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.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 server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.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 server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.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 - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.No sign-in (OAuth) metadata is published, so there are no sign-in addresses to check.not applicable
Source: our own test, 2026-10-26, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 1,776 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 9 tools, 0 resources, 0 prompts.
- 5,143 msFinished: 2 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.
“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. “io.github.revclamp/revclamp-mcp: MCP server record.” Data checked 2026-10-26. https://protocolprobe.com/mcp/servers/io.github.revclamp/revclamp-mcp
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
[](https://protocolprobe.com/mcp/servers/io.github.revclamp/revclamp-mcp)
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