MCP servers › org.omenz.www › agent-tools
MCP server · registry snapshot 2026-11-19 · last tested 2026-11-19
agent-tools MCP server
Registry name org.omenz.www/agent-tools
OMENZ agent tools — the publisher's title
by www.omenz.org · domain (the registry's namespace rule)Website ↗
Tools for agents that buy: Transaction Guard, Checkout, Settlement Rescue, budgets, x402 checks. — the publisher's description
Summary
org.omenz.www/agent-tools is a remote MCP server listed in the official MCP registry at version 1.1.0, under the namespace of the domain www.omenz.org. On 2026-11-19 ProtocolProbe connected to it in read-only mode and read its inventory: 102 tools, 0 resources and 0 prompts.
Record checks
1 of 2 record checks met · 7 do not apply
- met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: 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- not applicable: The version the registry lists can be installed and is not withdrawn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: no public GitHub repository
From public records, not a safety rating. Each check with its reason
Operate this server? Correct a fact · README badge · Run the checks yourself · Claim it
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
- Tools
- 102
- Last tested
- 2026-11-19
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-19 (www.omenz.org), 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 (1.1.0).
Observed fact
This server accepted a session without any credential and lists 10 tools whose name or declaration suggests they change data (locker_put, pobox_create, pobox_drop, receipt_put, failure_put and 5 more). That is our reading of the names; we did not call them. Source: our connection, 2026-11-19.
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-19
- Mode
- read-only (no tool calls)
- Latest version
- 1.1.0, published 2026-11-18 (registry, as of the 2026-11-19 snapshot)
- First listed version
- 2026-11-14 (earliest version still in the registry; older removed versions would be earlier)
- Version history
- 5 versions listed, 2026-11-14 to 2026-11-18; 5 in the 90 days before the 2026-11-19 snapshot.(versions still listed in the registry only)
Most recent 5 versions
1.1.0· 2026-11-181.0.3· 2026-11-161.0.2· 2026-11-141.0.1· 2026-11-141.0.0· 2026-11-14
- Registry data
- snapshot 2026-11-19
- Package and repository
- checked 2026-11-19
- 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. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. 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
Version 1.0.3 (published 2026-11-16) → 1.1.0 (published 2026-11-18), between the registry lists of 2026-11-18 and 2026-11-19.
No release note: the registry entry links no GitHub repository.
Source: the official MCP Registry list on 2026-11-18 and on 2026-11-19; release notes from the GitHub Releases API, checked 2026-11-19.
What it is
What does this server offer?
Observed inventoryNone of its 102 tools are described as changing anything. For 102 the reading was uncertain, so no mark is shown.
- agent_readyon 2 other servers
“Score 0-100 for how well AI assistants and agents can find, read and use a business website, with prioritized plain-language fixes.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
urlstringrequired“Public website URL”
- site_checkon 5 other servers
“Website health and business facts for one URL (alive, still theirs, readable; contact paths, structured data).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
urlstringrequired“Public website URL”
- changedon 1 other server
“Did a web page really change since your last visit?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
urlstringrequired“Public website URL”
- local_facts
“What a local business's OWN website says right now: phone, address, hours, and holiday/temporary-closure notices quoted word for word, each with its source.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
urlstringrequired“Public website URL”
- locker_puton 3 other servers
“Agent Locker: check a job's working state in (resume packet: objective, decisions, open_items, facts, permissions, next_action, pointers; any JSON object up to 64 KB) so it stops filling your context.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs, 1 required
packetobjectrequired“Resume packet, any JSON object up to 64 KB”ttl_daysinteger“1-30, default 7”tostring“Optional recipient label for handoffs”fromstring“Optional sender label”
- pobox_create
“Agent PO Box: create a mailbox address (box_id) other agents can drop messages into while you're offline; you get a private owner_key.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input
labelstring“label”
- pobox_drop
“Agent PO Box: leave a JSON message (<=16 KB) in another agent's box using its box_id.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs, 2 required
box_idstringrequired“PO box id from pobox/create”messagerequired“JSON object, list or string, <=16 KB”fromstring“from”subjectstring“subject”
- pobox_inbox
“Agent PO Box: open your waiting messages.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
box_idstringrequired“PO box id from pobox/create”ackstring“ack”x_owner_keystring“x owner key”
- receipt_put
“Receipt Locker: record a machine-readable receipt (payer, payee, amount, tx_hash, job, request/response hashes).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
11 inputs, 3 required
payerstringrequired“payer”payeestringrequired“payee”amountstringrequired“amount”currencystring“currency”networkstring“chain name, e.g.”tx_hashstring“tx hash”job_idstring“job id”servicestring“service”request_sha256string“request sha256”response_sha256string“response sha256”notestring“note”
- handoff_pack
“Handoff Packager: hand a job to another agent with only what it needs.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
6 inputs, 1 required
packetobjectrequired“packet”includearray“include”requiredarray“required”tostring“to”fromstring“from”ttl_daysinteger“ttl days”
- locker_geton 3 other servers
“Agent Locker: check a resume packet back out.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
idstringrequired“id returned by the create/put call”fieldsstring“Optional comma list of top-level keys”x_locker_keystring“x locker key”
- aliveon 1 other server
“Proof-of-Life: is this API/endpoint answering right now, before you spend money calling it?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
urlstringrequired“Endpoint URL to probe”methodstring“HTTP method the endpoint expects (default GET)”
Show 88 more tools
- quoteon 55 other servers
“Price Quote: the live x402 payment options of any endpoint, normalized: USD price, network, stablecoin, payTo, scheme, timeout; cheapest option.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
urlstringrequired“Endpoint URL to probe”methodstring“HTTP method the endpoint expects (default GET)”
- tx_preflighton 3 other servers
“Transaction Preflight: GO or STOP before your agent pays an x402 endpoint.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
7 inputs, 1 required
urlstringrequired“full https URL to check”methodstring“HTTP method of the target endpoint (GET or POST)”max_price_usdnumber“most you are willing to pay per call, in USD”expected_pay_tostring“payout wallet you expect (0x...), to catch swapped payees”networksarray“networks”listed_price_usdnumber“listed price usd”allow_testnetboolean“allow testnet”
- secret_scanon 6 other servers
“Secret-Leak Preflight: before a handoff, prompt or payload leaves your boundary, scan it for API keys (Anthropic, OpenAI, AWS, GitHub, Stripe, Slack, Google...), PEM keys, wallet private keys, recove…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
payloadrequired“String or JSON (<=256 KB) to check”
- spend_gate
“Spend Gate: ALLOW, DENY or ESCALATE before your agent spends money.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
policyobject“your spend policy, e.g.”spendobjectrequired“amount_usd required”
- branchon 3 other servers
“Branch Resolver: which location page of a multi-location business is the one you mean?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs, 1 required
urlstringrequired“full https URL to check”citystring“city”zipstring“zip”streetstring“street”
- failure_put
“Failure Receipt + Dead-Letter Queue: when a job fails, record WHY in a standard machine-readable form (omenz.failure.v0: objective, failed_step, error_class from a fixed list, attempts, money spent, …”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs, 1 required
failureobjectrequired“objective and failed_step required”tostring“to”fromstring“from”dlq_box_idstring“dlq box id”ttl_daysinteger“ttl days”
- terms_changed
“Terms Changed?: did an API or tool's pricing, limits or terms page change in a way that MATTERS?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
urlstringrequired“full https URL to check”previousstring“fingerprint from your last call”
- cost_estimateon 5 other servers
“Cost-to-Complete Estimate: what will this agent job cost BEFORE it starts?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
jobobjectrequired“job”
- passport_issueon 1 other server
“Permission Passport: issue a signed (Ed25519), expiring, job-scoped permission ticket for an agent: which tools, which hosts (plus explicit denies), how much it may spend, for how long (max 7 days).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
scopeobjectrequired“scope”
- passport_check
“Permission Passport check: ALLOW or DENY an agent's next action (tool, URL/host, amount, spent so far) against its passport, with reasons, spend left and time left.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
tokenstringrequired“token”actionobject“action”
- event_check
“Event Check: did a US public company actually FILE this news, or is it just going around?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 2 required
companystringrequired“ticker or company name”claimstringrequired“claim”daysinteger“lookback window, 1-365 (default 30)”
- claim_evidence
“Claim -> Evidence: does this source actually say what you're about to cite it for?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 2 required
claimstringrequired“claim”urlstringrequired“full https URL to check”
- preflighton 20 other servers
“Agent Preflight: can this agent finish the job with what it has, BEFORE it spends?”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
jobobjectrequired“job”
- ledger_createon 1 other server
“Agent Job Ledger: open an append-only, hash-chained record for one job (tool calls, spend, receipts, handoffs, failures, outputs, status).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs
job_idstring“job id”objectivestring“objective”x_ledger_keystring“the key returned by create (sent as a header on HTTP)”
- ledger_append
“Agent Job Ledger: append one entry (type tool_call|spend|receipt|handoff|failure|output|status|note|decision, any fields, amount_usd optional).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs, 2 required
ledger_idstringrequired“ledger id”entryobjectrequired“entry”x_ledger_keystring“the key returned by create (sent as a header on HTTP)”
- ledger_get
“Agent Job Ledger: read entries (since_seq for only new ones), totals (spent, counts by type, last status) and chain_intact: proof nothing was edited or removed.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
idstringrequired“id returned by the create/put call”since_seqinteger“since seq”x_ledger_keystring“the key returned by create (sent as a header on HTTP)”
- capability_card
“Agent Capability Card: a standard machine-readable card (omenz.capability-card.v0) of what any x402 service offers: endpoints, live prices and payment options, input/output examples from its discover…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
urlstringrequired“full https URL to check”methodstring“HTTP method of the target endpoint (GET or POST)”
- queue_create
“Agent Workforce: create a work queue for a team of agents.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs
name“name”supervisor_box_id“supervisor box id”lease_seconds“lease seconds”x_queue_keystring“the key returned by create (sent as a header on HTTP)”
- queue_enqueue
“Agent Workforce: add a job (title, payload, priority, not_before, repeat_every_minutes, max_attempts, bidding).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs
queue_id“queue id”title“title”payload“payload”priority“priority”x_queue_keystring“the key returned by create (sent as a header on HTTP)”
- queue_claimon 1 other server
“Agent Workforce: a worker claims the highest-priority ready job and gets a LEASE (it is now responsible).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs
queue_id“queue id”worker_id“worker id”x_queue_keystring“the key returned by create (sent as a header on HTTP)”
- queue_heartbeat
“Agent Workforce: worker is alive; extends its lease and stores a checkpoint (e.g.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs
queue_id“queue id”worker_id“worker id”item_id“item id”checkpoint“checkpoint”x_queue_keystring“the key returned by create (sent as a header on HTTP)”
- queue_complete
“Agent Workforce: worker finishes its leased job with a result; repeating jobs are rescheduled automatically.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs
queue_id“queue id”worker_id“worker id”item_id“item id”result“result”x_queue_keystring“the key returned by create (sent as a header on HTTP)”
- queue_fail
“Agent Workforce: worker reports failure; the job retries until max_attempts, then goes dead.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
6 inputs
queue_id“queue id”worker_id“worker id”item_id“item id”reason“reason”retry“retry”x_queue_keystring“the key returned by create (sent as a header on HTTP)”
- queue_escalate
“Agent Workforce: hand a job up to the supervisor (sealed drop into the supervisor's Agent PO Box).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs
queue_id“queue id”worker_id“worker id”item_id“item id”reason“reason”x_queue_keystring“the key returned by create (sent as a header on HTTP)”
- queue_resolve
“Agent Workforce: owner resolves an escalated/dead job: requeue, close or kill.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs
queue_id“queue id”item_id“item id”action“action”x_queue_keystring“the key returned by create (sent as a header on HTTP)”
- queue_bid
“Agent Workforce: worker bids on a job open for bidding (price_usd, eta_minutes).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
6 inputs
queue_id“queue id”worker_id“worker id”item_id“item id”price_usd“price usd”eta_minutes“eta minutes”x_queue_keystring“the key returned by create (sent as a header on HTTP)”
- queue_award
“Agent Workforce: owner awards a bidding job to one bidder; the award becomes that worker's lease.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs
queue_id“queue id”item_id“item id”worker_id“worker id”x_queue_keystring“the key returned by create (sent as a header on HTTP)”
- queue_statuson 2 other servers
“Agent Workforce: who is responsible for what right now (holders + lease time left), counts by state, escalations, roster (available/last seen/current job), scheduled jobs; or one item's full history …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs, 1 required
queue_idstringrequired“queue id”item_idstring“item id”x_queue_keystring“the key returned by create (sent as a header on HTTP)”
- market_find
“Agent Market: find the paid tool for a capability across ~35,000 x402 endpoints (Bazaar index, refreshed weekly).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
8 inputs, 1 required
qstringrequired“search text”needstring“need”max_price_usdnumber“most you are willing to pay per call, in USD”networkstring“chain name, e.g.”excludestring“exclude”limitinteger“limit”live_checkinteger“live check”min_payersinteger“min payers”
- market_reliability
“Micropayment Reliability Score: should your agent trust this paid endpoint?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
urlstringrequired“full https URL to check”methodstring“HTTP method of the target endpoint (GET or POST)”
- vendor_checkon 1 other server
“Vendor Due-Diligence Pack: before your agent depends on an unknown paid API: reliability score + the vendor domain's health (live/parked/moved) + its terms/pricing page digest (material lines) + flag…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
urlstringrequired“full https URL to check”methodstring“HTTP method of the target endpoint (GET or POST)”
- contract_build
“A2A Contract Builder: turn a machine job into signed terms both agents hold: deliverable, deterministic acceptance tests (required_fields, field_types, regex, min_items, max_bytes, equals, url_alive,…”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input, 1 required
termsobjectrequired“terms”
- contract_accept
“Acceptance Test as a Service + escrow verdict: a neutral party runs the contract's tests on what was delivered.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 2 required
tokenstringrequired“token”deliveredrequired“delivered”
- reputationon 3 other servers
“Reputation Receipts: an agent's job history as checked by OMENZ Acceptance Test: jobs, passed, failed, late, pass rate, distinct buyers (low = weak evidence), recent attestations.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
agentstringrequired“agent”
- evidence_bundleon 6 other servers
“Machine Evidence Bundle: package receipts, ledger heads, attestation tokens, claims and sources into one signed, hash-listed bundle (merkle-style root) that any agent can verify offline.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs, 1 required
itemsarrayrequired“items”labelstring“label”
- finance_reconcile
“Invoice/Payment Reconciler: invoice lines vs USDC-on-Base payments, each transaction checked on-chain (payer, payee, amount): MATCH / UNDERPAID / OVERPAID / MISSING / UNVERIFIED, duplicates and line-…”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs
invoice“invoice”payments“payments”
- finance_forecast
“Agent Budget Forecaster: spend history -> daily rate, next 7/30-day projection, trend, biggest dependencies.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input
spend“what you have spent so far, e.g.”
- finance_watchdog
“Subscription Watchdog: the paid endpoints your agent business relies on (up to 8): live price vs expected, down/up, terms/pricing page changed (pass back fingerprints).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
1 input
endpoints“endpoints”
- finance_snapshoton 1 other server
“Machine Warranty / Purchase Snapshot: signed record of exactly what a paid endpoint promised (live x402 requirements, description, examples) at purchase time.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
2 inputs
url“full https URL to check”method“HTTP method of the target endpoint (GET or POST)”
- finance_refund_request
“Structured Refund Request: order + failure receipt + payment receipts + purchase snapshot -> a standard signed dispute object with evidence strength and gaps.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs
order“order”failure“failure”receipt_ids“receipt ids”snapshot_token“snapshot token”remedy“remedy”
- terms_extract
“API Terms Extractor / Data-License Checker: before your agent uses a dataset or API commercially: a terms/license page -> clauses by category (commercial use, attribution, rate limits, retention, tra…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
urlstringrequired“full https URL to check”
- freshnesson 4 other servers
“Source Freshness / Result TTL: how long can your agent reuse a result before paying to fetch it again?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
urlstringrequired“full https URL to check”kindstring“kind”
- dedupeon 4 other servers
“Duplicate-Work Detector: before your agent pays to run a task, check whether someone in your team (same private namespace_key) already did it: normalized fingerprint -> HIT with the earlier result po…”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs, 2 required
namespace_keystringrequired“namespace key”taskrequired“task”result_pointerstring“result pointer”ttl_hoursinteger“ttl hours”
- context_diet
“Context Diet: shrink a packet before it fills your context: drops empty fields, dedupes lists, cuts long strings to a head + sha256 pointer, caps list length, always keeps required fields; reports by…”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs, 1 required
packetrequired“packet”requiredarray“required”max_string_charsinteger“max string chars”max_list_itemsinteger“max list items”
- wallet_balanceon 34 other servers
“Agent Wallet Balance: USDC and ETH balance of any wallet on Base (public chain data).”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
addressstringrequired“0x...”
- wallet_spend
“Agent Wallet Spend Report: what has this wallet been paying for?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
addressstringrequired“0x...”daysnumber“how many days to keep it (1-30)”
- wallet_runway
“Agent Wallet Runway: how many days before this agent wallet runs dry?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs, 1 required
addressstringrequired“0x...”daysnumber“how many days to keep it (1-30)”low_daysnumber“low days”critical_daysnumber“critical days”
- market_payee
“Payee Check: before paying an address, is it a known x402 seller?”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
addressstringrequired“0x...”
- market_price_index
“x402 Price Index / Fair Price Check: the going rate for a capability across listed x402 endpoints: comparables, sellers, min / p25 / median / p75 / max and usage-weighted median; pass price_usd (or a…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs, 1 required
qstringrequired“search text”price_usdnumber“price usd”urlstring“full https URL to check”min_payersinteger“min payers”
- authorizeon 5 other servers
“OMENZ Authorize: the authorization step for agent payments.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
7 inputs, 1 required
urlstringrequired“full https URL to check”methodstring“HTTP method of the target endpoint (GET or POST)”max_price_usdnumber“most you are willing to pay per call, in USD”expected_pay_tostring“payout wallet you expect (0x...), to catch swapped payees”policyobject“your spend policy, e.g.”spendobject“what you have spent so far, e.g.”passport_tokenstring“passport token”
- authorize_get
“OMENZ Authorize (GET form): same APPROVE / REVIEW / DECLINE check before paying an x402 endpoint, with query params: url, method, max_price_usd, expected_pay_to, daily_cap_usd, spent_today_usd.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
6 inputs, 1 required
urlstringrequired“full https URL to check”methodstring“HTTP method of the target endpoint (GET or POST)”max_price_usdnumber“most you are willing to pay per call, in USD”expected_pay_tostring“payout wallet you expect (0x...), to catch swapped payees”daily_cap_usdnumber“daily cap usd”spent_today_usdnumber“spent today usd”
- split_check
“Split Check: before paying into (or trusting) an on-chain revenue split, verify what it actually pays.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs, 1 required
addressstringrequired“0x...”networkstring“chain name, e.g.”claimedobject“claimed”beneficiarystring“beneficiary”
- credits_buy_1
“OMENZ prepaid credits: $1.00 balance in one x402 payment.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
Takes no inputs.
- credits_buy_5
“OMENZ prepaid credits: $5.00 balance in one x402 payment.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
Takes no inputs.
- market_reporton 6 other servers
“x402 Market Report (weekly): the supply side of the agent-payment economy: endpoints and sellers listed, how many get paid calls, price distribution, seller concentration (top 10 / top 50 share of ca…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
- market_sellers
“x402 Seller Lead List: sellers offering a capability (or all), with endpoints, 30-day calls, unique payers, price range, last-called date and an example endpoint; up to 500 rows.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
3 inputs
qstring“search text”min_payersinteger“min payers”limitinteger“limit”
- jacket_create
“Job Jacket: create the portable minimum working state for one assignment (objective, instructions, state, checkpoint, optional Permission Passport + Job Ledger link).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
8 inputs, 1 required
objectivestringrequired“objective”job_idstring“job id”instructionsstring“instructions”stateobject“state”checkpointstring“checkpoint”passport_tokenstring“passport token”ledger_idstring“ledger id”ttl_daysinteger“ttl days”
- jacket_checkout
“Job Jacket checkout: start a shift.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs, 1 required
workerstringrequired“worker”fieldsarray“fields”max_string_charsinteger“max string chars”lease_minutesinteger“lease minutes”take_overboolean“take over”
- jacket_checkin
“Job Jacket checkin: end a shift.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
6 inputs, 1 required
workerstringrequired“worker”state_patchobject“state patch”stateobject“state”checkpointstring“checkpoint”notestring“note”keep_leaseboolean“keep lease”
- jacket_history
“Job Jacket history: every version (who, when, checkpoint, note, state hash; never the contents) and the current lease.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
Takes no inputs.
- uptime_watch
“Uptime Watch: register a paid endpoint your agent depends on; OMENZ checks it daily (and on each report) for 30 days: up/down, latency, live x402 price and payTo, so you catch outages, price drift an…”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs, 1 required
urlstringrequired“full https URL to check”methodstring“HTTP method of the target endpoint (GET or POST)”daysinteger“how many days to keep it (1-30)”
- uptime_report
“Uptime Watch report: uptime %, median latency, incidents, price changes and payout-wallet changes for a watched endpoint, plus recent checks.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
idstringrequired“id returned by the create/put call”
- budget_create
“Shared Budget: one spending cap a whole TEAM of agents draws from (total, per day or per month), with a per-purchase max, an escalate line and allowed/blocked payees.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
9 inputs, 1 required
namestring“name”cap_usdnumberrequired“cap usd”periodstring“period”per_tx_max_usdnumber“per tx max usd”escalate_above_usdnumber“escalate above usd”allowed_recipientsarray“allowed recipients”blocked_recipientsarray“blocked recipients”ttl_daysinteger“ttl days”velocity_max_per_hourinteger“velocity max per hour”
- budget_spendon 1 other server
“Shared Budget: ask before each purchase.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
7 inputs, 2 required
budget_idstringrequired“budget id”amount_usdnumberrequired“amount usd”recipientstring“recipient”agentstring“agent”urlstring“full https URL to check”memostring“memo”idempotency_keystring“idempotency key”
- budget_release
“Shared Budget: give a recorded spend back to the cap when the purchase failed, was refunded or never happened.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs, 2 required
budget_idstringrequired“budget id”spend_idstringrequired“spend id”reasonstring“reason”
- budget_statuson 5 other servers
“Shared Budget: cap, spent, remaining this window, spend by agent and by payee, recent purchases.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs, 1 required
idstringrequired“id returned by the create/put call”limitinteger“limit”
- pay_verify
“Payment Verify: did this x402 payment really settle on Base?”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
7 inputs
tx_hashstring“tx hash”payment_responsestring“payment response”expected_pay_tostring“payout wallet you expect (0x...), to catch swapped payees”expected_payerstring“expected payer”expected_amount_usdnumber“expected amount usd”max_amount_usdnumber“max amount usd”min_confirmationsinteger“min confirmations”
- delivery_checkon 1 other server
“Delivery Check: you paid; did you get what was advertised?”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
6 inputs, 1 required
urlstring“full https URL to check”methodstring“HTTP method of the target endpoint (GET or POST)”deliveredrequired“delivered”schemaobject“schema”example“example”must_havearray“must have”
- market_cheapest
“Cheapest Working Tool: 'I need X' -> the cheapest x402 provider that ANSWERS right now.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
5 inputs, 1 required
qstringrequired“search text”max_price_usdnumber“most you are willing to pay per call, in USD”networkstring“chain name, e.g.”wantinteger“want”min_matchnumber“min match”
- spend_receipt
“Spend Receipt: one signed receipt per purchase: what your agent bought, why, what it cost (verified on Base from the tx hash or PAYMENT-RESPONSE) and what came back (checked against the seller's adve…”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
11 inputs, 1 required
urlstringrequired“full https URL to check”methodstring“HTTP method of the target endpoint (GET or POST)”tx_hashstring“tx hash”payment_responsestring“payment response”expected_pay_tostring“payout wallet you expect (0x...), to catch swapped payees”expected_amount_usdnumber“expected amount usd”delivered“delivered”schemaobject“schema”purposestring“purpose”agentstring“agent”job_idstring“job id”
- checkout_open
“OMENZ Checkout (open): ONE call before your agent pays any x402 seller.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
11 inputs
urlstring“full https URL to check”qstring“search text”methodstring“HTTP method of the target endpoint (GET or POST)”max_price_usdnumber“most you are willing to pay per call, in USD”expected_pay_tostring“payout wallet you expect (0x...), to catch swapped payees”budget_idstring“budget id”policyobject“your spend policy, e.g.”agentstring“agent”purposestring“purpose”job_idstring“job id”idempotency_keystring“idempotency key”
- checkout_close
“OMENZ Checkout (close): ONE call after paying.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
7 inputs, 1 required
checkout_idstringrequired“checkout id”tx_hashstring“tx hash”payment_responsestring“payment response”delivered“delivered”schemaobject“schema”not_paidboolean“not paid”release_if_unconfirmedboolean“release if unconfirmed”
- seller_record
“Seller Track Record: how an x402 seller actually performed for buyers who checked out through OMENZ: purchases closed, delivery rate, outcomes (good buy / paid not delivered), USDC settled (verified …”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
hoststringrequired“host”
- facilitators
“Facilitator Status + Router: which x402 facilitators are answering RIGHT NOW and which to use.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
4 inputs
networkstring“chain name, e.g.”schemestring“scheme”x402_versioninteger“x402 version”urlstring“full https URL to check”
- sale_record
“Sale Record (for SELLERS): after each x402 sale, your middleware sends the tx hash (or PAYMENT-RESPONSE) + the route sold.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
4 inputs, 1 required
urlstringrequired“full https URL to check”methodstring“HTTP method of the target endpoint (GET or POST)”tx_hashstring“tx hash”payment_responsestring“payment response”
- tx_decodeon 7 other servers
“Transaction Decode (Base): what did this transaction actually do, in plain English.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
tx_hashstringrequired“tx hash”
- name_resolveon 5 other servers
“Name Resolve: ENS (name.eth) and Basenames (name.base.eth) to address, or an address to its primary ENS name, forward-verified so a spoofed reverse record is flagged.”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
1 input, 1 required
qstringrequired“search text”
- settlement_cost
“Settlement Cost Check (Base): what moving money costs RIGHT NOW (live gas price, L1 data fee, ETH/USD from Chainlink on Base) for an x402 settlement (~86,550 gas, measured), a USDC transfer, an ETH t…”
Publisher declares: read-only yes · destructive no · idempotent yes · open-world yes
2 inputs
amount_usdnumber“amount usd”payments_per_dayinteger“payments per day”
- guardon 2 other servers
“OMENZ Transaction Guard: ONE call before money moves.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
12 inputs
urlstring“full https URL to check”qstring“search text”methodstring“HTTP method of the target endpoint (GET or POST)”payerstring“payer”quoted_price_usdnumber“quoted price usd”max_price_usdnumber“most you are willing to pay per call, in USD”expected_pay_tostring“payout wallet you expect (0x...), to catch swapped payees”purposestring“purpose”budget_idstring“budget id”policyobject“your spend policy, e.g.”agentstring“agent”dup_window_hoursinteger“dup window hours”
- budget_delegateon 1 other server
“Delegation Budget (agent allowances): a parent budget's OWNER gives a child agent its own bounded allowance: human/company -> supervisor agent -> workers -> sub-agents (4 levels).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
10 inputs, 2 required
budget_idstringrequired“budget id”namestring“name”cap_usdnumberrequired“cap usd”periodstring“period”per_tx_max_usdnumber“per tx max usd”escalate_above_usdnumber“escalate above usd”allowed_recipientsarray“allowed recipients”blocked_recipientsarray“blocked recipients”velocity_max_per_hourinteger“velocity max per hour”ttl_daysinteger“ttl days”
- settlement_rescue
“Settlement Rescue: 'payment weird?”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
7 inputs
payment_headerstring“payment header”authorizationobject“authorization”tx_hashstring“tx hash”payerstring“payer”pay_tostring“pay to”amount_usdnumber“amount usd”window_hoursinteger“window hours”
- market_job
“OMENZ Market job desk: tell OMENZ the JOB ('token price', 'weather by city', 'company enrichment by domain').”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
7 inputs, 1 required
needstringrequired“need”max_price_usdnumber“most you are willing to pay per call, in USD”networkstring“chain name, e.g.”wantinteger“want”purposestring“purpose”payerstring“payer”budget_idstring“budget id”
- market_job_guarded
“OMENZ Market job desk + Transaction Guard in one call: find the working provider for your job, then GO / CAUTION / STOP with budget, counterparty, duplicate payment (send payer), quoted price, settle…”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs, 1 required
needstringrequired“need”max_price_usdnumber“most you are willing to pay per call, in USD”payerstring“payer”budget_idstring“budget id”purposestring“purpose”
- dispute_packeton 1 other server
“Dispute Packet: a purchase went bad (not delivered, wrong output, partial, overcharged, duplicate).”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
14 inputs
checkout_idstring“checkout id”urlstring“full https URL to check”methodstring“HTTP method of the target endpoint (GET or POST)”tx_hashstring“tx hash”payment_headerstring“payment header”payerstring“payer”pay_tostring“pay to”amount_usdnumber“amount usd”delivered“delivered”schemaobject“schema”issuestring“issue”whatstring“what”sellerstring“seller”amount_requested_usdnumber“amount requested usd”
- po_issue
“Agent Purchase Order: whoever controls the money pre-approves ONE purchase: 'this agent may spend up to $X with seller Y (payTo and/or host) for Z, until T'.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
8 inputs, 1 required
max_usdnumberrequired“max usd”pay_tostring“pay to”sellerstring“seller”forstring“for”agentstring“agent”budget_idstring“budget id”job_idstring“job id”expires_in_hoursnumber“expires in hours”
- po_redeem
“Agent Purchase Order redeem: the buyer agent (or the seller, before serving) checks a PO right before paying: signature, expiry, payee, seller, amount <= max, and that it was never used.”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
5 inputs, 2 required
tokenstringrequired“token”amount_usdnumberrequired“amount usd”pay_tostring“pay to”sellerstring“seller”urlstring“full https URL to check”
- loadout_check
“OMENZ Loadout Check: will this job loadout (Agent Skin or robot loadout like HOST MODE, PERSONAL TRAINER, RECEPTIONIST) run on this robot or agent?”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs, 1 required
loadoutrequired“preset id (GET /v1/loadouts) or an omenz.loadout.v0 object”platform“platform profile id or a custom {id, native, addon} manifest”allow_addonsboolean“allow addons”
- loadout_compile
“OMENZ Loadout Compile: turn a loadout into the platform plan (nav2 action goals for ros-mcp, unitree_sdk2 calls, or MCP tools + an Authorize passport request) plus an Ed25519-signed install receipt (…”
Publisher declares: read-only no · destructive no · idempotent no · open-world yes
3 inputs, 1 required
loadoutrequired“preset id (GET /v1/loadouts) or an omenz.loadout.v0 object”platform“platform profile id or a custom {id, native, addon} manifest”allow_addonsboolean“allow addons”
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. The first 100 of 102 tools are listed. Read 2026-11-19.
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 390
- Tools with a description
- 100% of 102
- Typical description length
- 445 characters
The tool set
Counted from the listing
- Tools
- 102
- Size of the list
- about 24,267 tokens for an agent to load (characters ÷ 4)
- Naming
- 91 of 102 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 102 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, 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 remote endpoint (Streamable HTTP)
We connected to this URL on 2026-11-19 (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://www.omenz.org/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"agent-tools": {
"url": "https://www.omenz.org/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"agent-tools": {
"type": "http",
"url": "https://www.omenz.org/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"agent-tools","type":"http","url":"https://www.omenz.org/mcp"}'Claude Code
claude mcp add --transport http agent-tools https://www.omenz.org/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"agent-tools": {
"type": "streamableHttp",
"url": "https://www.omenz.org/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"agent-tools": {
"httpUrl": "https://www.omenz.org/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.agent-tools] url = "https://www.omenz.org/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"agent-tools": {
"url": "https://www.omenz.org/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://www.omenz.org/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.
What do the published files and outside lists say?
Read as text · nothing run · no tool called
Package files
- MCP SDK in the package files. Not read yet: added with the next daily run.
- Build workflow. Not read yet: added with the next daily run.
Outside lists
- CVE records (NVD). No CVE record in the NVD feeds we read links this server's repository. Source: read 2026-11-19. This product uses the NVD API but is not endorsed or certified by the NVD.
- GitHub advisories. No GitHub advisory names this entry's listed package. Source: read 2026-11-19. GitHub Advisory Database, CC BY 4.0
- Docker MCP catalogue. Not in the Docker MCP catalogue on 2026-11-19. Source: read 2026-11-19.
- Cline marketplace. Not in the Cline marketplace on 2026-11-19. Source: read 2026-11-19.
Own host
- security.txt. No security.txt at https://www.omenz.org/.well-known/ (HTTP 404, 2026-11-19). No security.txt at https://omenz.org/.well-known/ (HTTP 404, 2026-11-19). Source: www.omenz.org/.well-known/security.txt · read 2026-11-19.
- A2A agent card. An A2A agent card is published at https://www.omenz.org/.well-known/agent-card.json (name, skills, url). An A2A agent card is published at https://omenz.org/.well-known/agent-card.json (name, skills, url). Source: www.omenz.org/.well-known/agent-card.json · read 2026-11-19.
Read as text from published files and outside lists. Nothing was installed or run, and no tool was called. A fact, not a rating. How each fact is read
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 www.omenz.org/mcp | Session opened | matches | our test · 2026-11-19 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-19 |
Tool list changes
Our reads compared · no tool calledHosted endpoint www.omenz.org/mcp
2 of 2 comparisons between consecutive reads showed a change (3 reads, 2026-11-15 to 2026-11-19; versions 1.0.2 to 1.1.0).
Last change seen between our reads on 2026-11-17 (version 1.0.3) and 2026-11-19 (version 1.1.0).
Added (28) (25 shown):
budget_createbudget_delegatebudget_releasebudget_spendbudget_statuscheckout_closecheckout_opendelivery_checkdispute_packetfacilitatorsguardloadout_checkloadout_compileloadout_simulatemarket_cheapestmarket_jobmarket_job_guardedname_resolvepay_verifypo_issuepo_redeemrobot_action_gatesale_recordseller_recordsettlement_costand 3 more.
Changed (30) (25 shown):
alive: descriptionauthorize: descriptionauthorize_get: descriptioncontext_diet: descriptiondedupe: descriptionfreshness: descriptionjacket_history: descriptionledger_append: descriptionledger_get: descriptionlocker_get: descriptionmarket_payee: descriptionpassport_check: descriptionpobox_create: descriptionpobox_drop: descriptionpobox_inbox: descriptionqueue_award: descriptionqueue_bid: descriptionqueue_claim: descriptionqueue_complete: descriptionqueue_enqueue: descriptionqueue_escalate: descriptionqueue_fail: descriptionqueue_heartbeat: descriptionqueue_resolve: descriptionqueue_status: descriptionand 5 more.
Compared from the tool lists our read-only connection recorded, separately for each hosted endpoint and each package: each tool's name, title, description, input schema and annotations (the order of keys and of tools is ignored). We see a list only when we read it: a change is shown between the two reads where we first saw it, and anything after 2026-11-19 is not known yet. No tool was called. How it is compared
Choosing
Record checks
Public records · not a safety rating1 of 2 record checks met · 7 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- 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 2026-11-19. 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, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about org.omenz.www/agent-tools
Answered from the data aboveWho publishes org.omenz.www/agent-tools?
The registry ties the namespace org.omenz.www to the domain www.omenz.org; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.
Does org.omenz.www/agent-tools need an API key or sign-in?
It opened a session without any credential on 2026-11-19. The registry entry declares no required credential; no declaration is not a guarantee.
Has org.omenz.www/agent-tools been security tested?
Partly. 2 of the 14 checks that apply to it were exercised. It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. ProtocolProbe publishes no security verdict for a named server.
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
Open without sign-in
It accepted a session without any credential and lists tools whose names suggest they change data. We did not call them. 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. These 18 checks are separate from the record checks at the top of this page, which read public records only.
- 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, except for a server whose operator has claimed it and given permission (that server's page says so); 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, except for a server whose operator has claimed it and given permission (that server's page says so); 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, except for a server whose operator has claimed it and given permission (that server's page says so); 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, except for a server whose operator has claimed it and given permission (that server's page says so); 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, except for a server whose operator has claimed it and given permission (that server's page says so); 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, 2026-11-19, 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
- 1,689 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 102 tools, 0 resources, 0 prompts.
- 5,757 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. “org.omenz.www/agent-tools: MCP server record.” Data checked 2026-11-19. https://protocolprobe.com/mcp/servers/org.omenz.www/agent-tools
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/org.omenz.www/agent-tools)
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, except for a server whose operator has claimed it and given permission (that server's page says so).
Write to hello@protocolprobe.com · corrections log · methodology