# Agent evidence (pypi · agent-evidence-mcp)

Offline, read-only tools that verify AI claims against evidence and replay conformance vectors.

- Trust score: 83/100 (high trust)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-05

## Components

- pypi · `agent-evidence-mcp`: 83/100 (this document), [markdown](https://verifymcp.io/servers/probityai-agent-evidence-mcp/agent-evidence-mcp.md), [page](https://verifymcp.io/servers/probityai-agent-evidence-mcp/agent-evidence-mcp)

## Channel facts

- Registry: `pypi`
- Package: `agent-evidence-mcp`
- Version: `0.2.5`
- 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**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs setuptools.build_meta at install time, a recognised build step with no custom scripting around it.
  - 1 of 37 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 100/100
  - Source repository is publicly reachable at the declared URL.
  - Cryptographically verified build provenance (signed, bound to probityai/probity).
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 3 days ago).
  - Publishes a security disclosure policy (SECURITY.md).
- **Schema Quality & AI Usability**: 55/100
  - AI-judged instruction clarity (fair).
  - Tool/resource definitions use about 402 tokens (~44/item across 9 items; 9 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 53/100
  - Stability observed for 16 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 10 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the Agent evidence MCP server?

Agent evidence runs locally as a PyPI package, launched with uvx agent-evidence-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 probityai-agent-evidence-mcp -- uvx agent-evidence-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "probityai-agent-evidence-mcp": {
      "command": "uvx",
      "args": [
        "agent-evidence-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "probityai-agent-evidence-mcp": {
      "command": "uvx",
      "args": [
        "agent-evidence-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add probityai-agent-evidence-mcp -- uvx agent-evidence-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "probityai-agent-evidence-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "agent-evidence-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add probityai-agent-evidence-mcp --command uvx --arg agent-evidence-mcp
```

### Hermes

```yaml
mcp_servers:
  probityai-agent-evidence-mcp:
    command: "uvx"
    args: ["agent-evidence-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "probityai-agent-evidence-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "agent-evidence-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add probityai-agent-evidence-mcp -t stdio -c uvx -a agent-evidence-mcp
```

### Other

```json
{
  "mcpServers": {
    "probityai-agent-evidence-mcp": {
      "command": "uvx",
      "args": [
        "agent-evidence-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.

### 2026-11-04 (score 83, +1)

No change was recorded against any check on this day. Stability & Change Management went from 47 to 50. That category is still filling its 30-day observation window: 14 days of observed history at the previous scan, 15 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-02 (score 82, +32)

- [security improvement] Injection markers: unverified → pass
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] Stability: unverified → 0.43
- [functional improvement] MCP protocol: unverified → pass

### 2026-11-01 (score 50, −30)

- [security regression] Stability: 0.37 → unverified
- [security regression] Tool safety: pass → unverified
- [security] The attested source repository moved: probityai/agent-evidence-mcp → probityai/probity
- [functional regression] Capabilities: pass → unverified
- [functional regression] Tool coverage: 100 → unverified
- [functional improvement] Security disclosure: fail → pass
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.2.4 → 0.2.5

### 2026-10-30 (score 80, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 79, +11)

- [security regression] Provenance: fail → unverified
- [security improvement] Provenance: fail → pass
- [security] The attested source repository moved: probityai/agent-evidence-mcp
- [functional] Package version: 0.2.0 → 0.2.4
- [functional] Package version: 0.2.0 → 0.2.3

### 2026-10-27 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-25 (score 67, +2)

- [functional improvement] Stability: unverified → 0.17

### 2026-10-21 (score 65, +15)

- [security improvement] Malware scan: unverified → pass

## MCP tools (9)

### `verify_claim` (~43 tokens)

Verify a claim against evidence

Decide one claim against evidence bytes the caller supplies, with probity-verify.

Input parameters:

- `artifacts`
- `case` (object, required)
- `policy` (object, required)

### `verify_sample` (~30 tokens)

Run a bundled sample claim

Run a bundled sample claim: contradicted, not_established or supported.

Input parameters:

- `scenario` (string, required)

### `list_vector_corpora` (~27 tokens)

List conformance vector corpora

Name every shipped corpus with its suite revision and vector counts where it declares them.

### `run_vectors` (~46 tokens)

Replay a conformance vector corpus

Replay one corpus with the bundled reference verifier; per-vector rows come back in pages.

Input parameters:

- `corpus` (string)
- `limit` (integer)
- `offset` (integer)

### `explain_vector` (~41 tokens)

Explain one conformance vector

Return one vector: its manifest entry, the conditions it tests, and its input bytes.

Input parameters:

- `corpus` (string)
- `vector_id` (string, required)

### `lookup_term` (~32 tokens)

Look up a vocabulary term

Look a term up in the released vocabulary by exact key; otherwise suggest close keys.

Input parameters:

- `term` (string, required)

### `check_artifact_digest` (~51 tokens)

Check an artifact digest against a document

Check that an artifact has a digest a TEA, CycloneDX or in-toto document names.

Input parameters:

- `artifact_base64`
- `artifact_text`
- `document` (string, required)

### `canonicalize_json` (~45 tokens)

Canonicalize JSON under RFC 8785

Admit one JSON document and return its RFC 8785 canonical bytes, with the jcs-admit crate.

Input parameters:

- `document` (string, required)
- `profile` (string)

### `verify_dsse` (~51 tokens)

Verify a DSSE envelope

Verify a DSSE envelope against Ed25519 keys the caller trusts, with the dsse crate.

Input parameters:

- `envelope` (string, required)
- `threshold` (integer)
- `trusted_keys` (array, required)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/probityai-agent-evidence-mcp/agent-evidence-mcp#diagnostics

## Score history

- 2026-11-05: 83
- 2026-11-04: 83
- 2026-11-03: 82
- 2026-11-02: 82
- 2026-11-01: 50
- 2026-10-31: 80
- 2026-10-30: 80
- 2026-10-29: 79
- 2026-10-28: 68
- 2026-10-27: 68
- 2026-10-26: 67
- 2026-10-25: 67
- 2026-10-24: 65
- 2026-10-23: 65
- 2026-10-22: 65
- 2026-10-21: 65
- 2026-10-20: 50

## Common questions

### What is the Agent evidence MCP server?

Agent evidence is an MCP server listed in the public MCP registry as io.github.probityai/agent-evidence-mcp. Offline, read-only tools that verify AI claims against evidence and replay conformance vectors. This page covers its PyPI package (agent-evidence-mcp).

### Is the Agent evidence MCP server safe to use?

Agent evidence scores 83 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 5 November 2026. Its build provenance is signed and verified. 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 Agent evidence MCP server expose?

Agent evidence exposes 9 tools: verify_claim, verify_sample, list_vector_corpora, run_vectors, explain_vector, and 4 more. Their descriptions and schemas cost roughly 366 tokens of context every time the server is loaded.

### Is the Agent evidence MCP server still maintained?

Agent evidence 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 Agent evidence MCP server under?

Agent evidence declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

### What did VerifyMCP test on the Agent evidence MCP server?

VerifyMCP ran 16 checks on Agent evidence, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- PyPI project: https://pypi.org/project/agent-evidence-mcp/
- Socket report: https://socket.dev/pypi/package/agent-evidence-mcp
- Repository: https://github.com/probityai/probity
- Changelog RSS feed: https://verifymcp.io/servers/probityai-agent-evidence-mcp/agent-evidence-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/probityai-agent-evidence-mcp/agent-evidence-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/probityai-agent-evidence-mcp/agent-evidence-mcp.json
- HTML version of this page: https://verifymcp.io/servers/probityai-agent-evidence-mcp/agent-evidence-mcp