English Français العربية

Agent evidence

Official registry Data and databases

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

Source code Documentation

Install

Add this to your client's MCP configuration (Claude Desktop: claude_desktop_config.json; Cursor: .cursor/mcp.json; VS Code and others use the same "mcpServers" shape).

PYPI package agent-evidence-mcp
Claude Code 
claude mcp add agent-evidence -- uvx agent-evidence-mcp==0.2.0
JSON configuration (Claude Desktop, Cursor, VS Code) 
{
    "mcpServers": {
        "agent-evidence": {
            "command": "uvx",
            "args": [
                "agent-evidence-mcp==0.2.0"
            ]
        }
    }
}

Documentation

From the project's README on GitHub, refreshed weekly. Links open on GitHub.

Contents
  1. agent-evidence-mcp
  2. Quick start
  3. Tools
  4. Status
  5. Documentation
  6. License

agent-evidence-mcp

An offline, read-only MCP server that decides whether a claim about an AI system holds against evidence bytes you supply, and replays the agent-evidence conformance vectors.

It's for agent builders, auditors and platform engineers who want their assistant to check evidence instead of trusting a report.

Install the released package: pip install agent-evidence-mcp==0.2.0. It pins probity-verify==0.1.1, agent-evidence-vectors==0.23.0, agent-evidence-vocabulary==0.6.0, agent-evidence-admission==0.1.2 and jcs-admit==0.1.0 exactly. The last one carries the jcs-admit and dsse Rust crates as wheels.

Quick start

Add it to Claude Code, then ask the assistant to run the sample claim:

claude mcp add agent-evidence -- uvx agent-evidence-mcp@0.2.0

Or install the Claude Code plugin: /plugin install agent-evidence --marketplace probityai/agent-evidence-mcp.

Or call a tool from Python, with no client installed beyond the package:

uvx --from agent-evidence-mcp==0.2.0 python - <<'PY'
import asyncio
from mcp.client import Client
from mcp.client.stdio import StdioServerParameters

async def main():
    async with Client(StdioServerParameters(command="agent-evidence-mcp")) as client:
        result = await client.call_tool("verify_sample", {"scenario": "contradicted"})
        print(result.structured_content["decision"], result.structured_content["reason"])

asyncio.run(main())
PY

It prints:

contradicted selected_span_missing_from_record

A passage the report quotes is missing from the source capture, so the claim is contradicted. Use supported or not_established as the scenario for the other two decisions.

Tools

Nine tools, all read-only, offline and bounded: verify_claim, verify_sample, list_vector_corpora, run_vectors, explain_vector, lookup_term and check_artifact_digest, canonicalize_json and verify_dsse. Nothing is fetched, written or sent.

Status

Version 0.2.0. The tests run every tool through a real MCP client against the shipped corpus, and a mutation check confirms they fail when a tool's output is broken.

Documentation

pageread it for
Toolsevery tool, its arguments and what it returns
InstallClaude Code, Gemini CLI, Docker and plain stdio
Agent guidea short index for agents using the server
Changing the repositorythe commands to run and what never to hand-edit

License

Apache-2.0.

Frequently asked questions

What is Agent evidence?

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

How do I install Agent evidence?

It runs on your machine. In Claude Code: claude mcp add agent-evidence -- uvx agent-evidence-mcp==0.2.0. For other clients, paste the JSON configuration from this page into their MCP settings.

Does Agent evidence need an API key?

Its registry entry lists no required key or secret. Some features may still need an account with the service it connects to.

Is Agent evidence open source?

Yes. Its code is on GitHub under the Apache-2.0 license.

Who maintains Agent evidence?

It is published by probityai. AI.tn lists it but does not maintain or endorse it.

From the official MCP Registry. Listing is not an endorsement: review a server's code and permissions before giving it access to your data.