# Agents Trust (npm · @agents-trust/mcp)

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

- Trust score: 71/100 (medium)
- Change this week: +5
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- npm · `@agents-trust/mcp`: 71/100 (this document), [markdown](https://verifymcp.io/servers/com-agents-trust-recommend/agents-trust-mcp.md), [page](https://verifymcp.io/servers/com-agents-trust-recommend/agents-trust-mcp)

## Channel facts

- Registry: `npm`
- Package: `@agents-trust/mcp`
- Version: `0.1.4`
- Transport: `stdio`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-05.

- **Supply Chain Security**: 90/100
  - No malware found by supply-chain analysis.
  - CVE check failed: a known high-severity CVE affects zod 3.25.76, reached via @x402/core > zod. A fixed version is available.
  - No install/post-install scripts declared.
  - 30 of 114 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 8 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 69/100
  - AI-judged instruction clarity (excellent).
  - 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.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 4 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## 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.

### Claude

```bash
claude mcp add com-agents-trust-recommend -- npx -y @agents-trust/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "com-agents-trust-recommend": {
      "command": "npx",
      "args": [
        "-y",
        "@agents-trust/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "com-agents-trust-recommend": {
      "command": "npx",
      "args": [
        "-y",
        "@agents-trust/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add com-agents-trust-recommend -- npx -y @agents-trust/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-agents-trust-recommend": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@agents-trust/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add com-agents-trust-recommend --command npx --arg -y --arg @agents-trust/mcp
```

### Hermes

```yaml
mcp_servers:
  com-agents-trust-recommend:
    command: "npx"
    args: ["-y", "@agents-trust/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "com-agents-trust-recommend": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@agents-trust/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add com-agents-trust-recommend -t stdio -c npx -a -y @agents-trust/mcp
```

### Other

```json
{
  "mcpServers": {
    "com-agents-trust-recommend": {
      "command": "npx",
      "args": [
        "-y",
        "@agents-trust/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-05 (score 71, +1)

No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-04 (score 70, +4)

- [functional improvement] Stability: unverified → 0.27

### 2026-10-28 (score 66, +23)

- [security regression] CVE-2023-54404 affects this package: high
- [security regression] Known CVEs: unverified → fail
- [security improvement] Malware scan: unverified → pass
- [functional improvement] Dependency health: unverified → 0.89

### 2026-10-27 (score 43)

First indexed and scored.

## MCP tools (4)

### `recommend` (~490 tokens)

Recommend paid APIs for a task

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.

Input parameters:

- `chain` (string): Only return providers that accept payment on this network, as a CAIP-2 id, e.g. eip155:8453 for Base.
- `limit` (integer): Maximum number of picks, 1–5. Default 3.
- `live` (number): Only 1 is accepted, which is also the default: prefer endpoints with recent liveness evidence.
- `max_price_usd` (number): 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.
- `need` (string, required): The 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.
- `view` (string): 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).

### `inspect` (~369 tokens)

Inspect evidence for one endpoint

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.

Input parameters:

- `url` (string, required): Exact 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.
- `view` (string): Response detail: compact (smallest), evidence (full evidence blocks), legacy (default, original field layout) or debug (adds diagnostic fields).

### `receipt` (~142 tokens)

Check payment settlement

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.

Input parameters:

- `payment_attempt_id` (string, required): The payment_attempt_id returned by a paid recommend or inspect call: a lowercase UUIDv7. Copy it unchanged.

### `health` (~62 tokens)

Check service version

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).

## Diagnostics

Captured diagnostic sections: Provenance, Vulnerabilities, Dependencies. The full working is on the page: https://verifymcp.io/servers/com-agents-trust-recommend/agents-trust-mcp#diagnostics

## Score history

- 2026-11-05: 71
- 2026-11-04: 70
- 2026-11-03: 66
- 2026-11-02: 66
- 2026-11-01: 66
- 2026-10-31: 66
- 2026-10-30: 66
- 2026-10-29: 66
- 2026-10-28: 66
- 2026-10-27: 43

## 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 71 out of 100 on VerifyMCP. We recorded 1 known advisory against it as of 5 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 5 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.

## Links

- npm package: https://www.npmjs.com/package/@agents-trust/mcp
- Socket report: https://socket.dev/npm/package/@agents-trust/mcp
- Repository: https://github.com/agents-trust/agents-trust-mcp
- Website: https://agents-trust.com/
- Changelog RSS feed: https://verifymcp.io/servers/com-agents-trust-recommend/agents-trust-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/com-agents-trust-recommend/agents-trust-mcp.json
- HTML version of this page: https://verifymcp.io/servers/com-agents-trust-recommend/agents-trust-mcp