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.

agent-evidence is the open record format; probityai checks and grades records against it, and this server runs those checks for an assistant.

Install the released package: pip install agent-evidence-mcp==0.2.5. It takes the packages of its own family (probity-verify, agent-evidence-vectors, agent-evidence-vocabulary, agent-evidence-admission, jcs-admit) as compatible-release ranges, so it installs beside their latest releases, and pins every third-party dependency 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@0.2.5

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

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

uvx --from agent-evidence-mcp==0.2.5 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 0.2.5. 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

page	read it for
Tools	every tool, its arguments and what it returns
Install	Claude Code, Gemini CLI, Docker and plain stdio
Agent guide	a short index for agents using the server
Changing the repository	the commands to run and what never to hand-edit