Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Agents Trust

NPM · @AGENTS-TRUST/MCP

Find APIs and inspect endpoint evidence. Pay with your own Base USDC wallet.

Available components

+4 this week 70 Trust /100

Last scanned (23 hours ago)

Scores higher than 38% of npm servers

Category Search and Retrieval

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security90
  • No malware found by supply-chain analysis.Pass
  • CVE check failed: a known high-severity CVE affects zod 3.25.76, reached via @x402/core > zod. A fixed version is available. View diagnostics → Fail
  • No install/post-install scripts declared.Pass
  • 30 of 114 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability69
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1063 tokens (~265/item across 4 items; 4 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management27
  • Stability observed for 8 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 4 Nov 26 +4
    • Stability: unverified → 0.27 ▲ functional
  • 28 Oct 26 +23
    • CVE-2023-54404 affects this package: high ▼ security
    • Known CVEs: unverified → fail ▼ security
    • Malware scan: unverified → pass ▲ security
    • Dependency health: unverified → 0.89 ▲ functional
  • 27 Oct 26 43

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 4 Nov 2026 · Analysed npm/@agents-trust/mcp@0.1.4

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Vulnerabilities 1 finding
ID CVE Severity Vector Fix available
GHSA-mrhx-c7xc-m3w5 CVE-2023-54404 high CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:N/I:N/A:H yes

Background: What a vulnerability scan can and cannot prove →

Dependencies 114 packages
Packages resolved 114
Stale 30
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 4 exposed · ~1,063 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
health ~62

Check that the Agents Trust API is reachable and read its deployed version. Free, read-only, no parameters. Use it to diagnose connection problems before retrying recommend or inspect; it does not measure data freshness. Returns data.status ("ok") and data.version (deployment identifier).

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

inspect ~369

Read the stored evidence for one exact x402 endpoint URL: price, payment networks, liveness, delivery history and risk flags. It never calls or pays the endpoint itself. Use it before paying an endpoint you already know, for example one returned by recommend; use recommend instead to find candidates for a task. Pass url exactly as listed: paths and trailing slashes are distinct. Use view=compact for essentials only. Demo endpoints are free; other indexed endpoints cost 1% of the endpoint's lowest quoted price, minimum 0.001 USDC. An unindexed URL returns ENDPOINT_NOT_INDEXED without payment. Pays only if the wallet owner set AGENTS_TRUST_ENABLE_PAYMENTS=true and AGENTS_TRUST_WALLET_PRIVATE_KEY (Base USDC): one paid call per process, at most AGENTS_TRUST_MAX_CALL_USDC (default 0.01), never retried. Otherwise it errors without paying; errors and empty results are free. Returns JSON {data, payment_attempt_id, request_id}; payment_attempt_id is set only after a paid answer, for use with receipt. data.endpoint holds price (min_usd, max_usd), networks and payment_offers, liveness (is_live, last probe time; compact and evidence views), delivery_verification (status, charged and charged-not-delivered counts), risk_flags and invocation (request schema); data.lookup shows the canonical URL matched.

NameTypeReqDescription
urlstringyesExact public HTTPS endpoint URL, including any fixed query parameters, e.g. a pick's url from recommend. Private, malformed and credential-bearing URLs are rejected before payment.
viewstring–Response detail: compact (smallest), evidence (full evidence blocks), legacy (default, original field layout) or debug (adds diagnostic fields).

No output schema declared.

No examples provided.

receipt ~142

Check whether a paid recommend or inspect answer has settled on-chain. Free, read-only, and never repeats the paid request. Use it after a paid call, with the payment_attempt_id that call returned; answers arrive before settlement completes. Returns data.state (pending, settled, settle_failed_after_answer or settle_unknown_after_answer) and data.transaction (transaction hash once settled, else null). An unknown id returns a not-found error. Pending or unavailable does not prove that no money moved: check the wallet before paying again.

NameTypeReqDescription
payment_attempt_idstringyesThe payment_attempt_id returned by a paid recommend or inspect call: a lowercase UUIDv7. Copy it unchanged.

No output schema declared.

No examples provided.

recommend ~490

Find which paid x402 API to call for a task described in plain words, ranked with evidence. Each pick has the endpoint URL, provider price and payment network, a ready request template, liveness, delivery evidence and risk flags. Use it when you do not yet know which API to call; use inspect instead when you already have one exact endpoint URL, and receipt to confirm settlement after paying. Write need as the task itself ("current weather in Paris"), not a product name; narrow with max_price_usd or chain, and use view=compact to save tokens. Free demo: need exactly "weather", "crypto prices" or "web search" (any case); every other need, including longer weather phrasings, costs 0.01 USDC. Pays only if the wallet owner set AGENTS_TRUST_ENABLE_PAYMENTS=true and AGENTS_TRUST_WALLET_PRIVATE_KEY (Base USDC): one paid call per process, at most AGENTS_TRUST_MAX_CALL_USDC (default 0.01), never retried. Otherwise it errors without paying; errors and empty results are free. Returns JSON {data, payment_attempt_id, request_id}; payment_attempt_id is set only after a paid answer, for use with receipt. data.picks may be shorter than limit, or empty, when evidence is insufficient.

NameTypeReqDescription
chainstring–Only return providers that accept payment on this network, as a CAIP-2 id, e.g. eip155:8453 for Base.
limitinteger–Maximum number of picks, 1–5. Default 3.
livenumber–Only 1 is accepted, which is also the default: prefer endpoints with recent liveness evidence.
max_price_usdnumber–Highest provider price per call in USD you accept. Separate from the 0.01 USDC recommendation fee; the provider's own quote at call time is authoritative.
needstringyesThe work you need done, in plain words, e.g. "weather forecast for Berlin" or "translate text to German". 2–300 characters with at least two letters or digits.
viewstring–Response detail: compact (smallest, pick essentials and request template), evidence (adds ranking, liveness, delivery and payment evidence per pick) or legacy (default, original field layout).

No output schema declared.

No examples provided.

Install

How do I install the Agents Trust MCP server?

Agents Trust runs locally as an npm package, launched with npx -y @agents-trust/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · @agents-trust/mcp

# add to Claude Code
claude mcp add com-agents-trust-recommend -- npx -y @agents-trust/mcp
Common questions

What is the Agents Trust MCP server?

Agents Trust is an MCP server listed in the public MCP registry as com.agents-trust/recommend. Find APIs and inspect endpoint evidence. Pay with your own Base USDC wallet. This page covers its npm package (@agents-trust/mcp).

Is the Agents Trust MCP server safe to use?

Agents Trust scores 70 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 4 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Agents Trust MCP server expose?

Agents Trust exposes 4 tools: recommend, inspect, receipt, health. Their descriptions and schemas cost roughly 1,063 tokens of context every time the server is loaded.

Is the Agents Trust MCP server still maintained?

Agents Trust is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Agents Trust MCP server under?

Agents Trust declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.