Catalog PyPI
PACKAGE EXPLORERView in registry

agent-evidence-mcp

PyPI

Offline, read-only MCP server that verifies agent evidence claims and replays the agent-evidence conformance vectors

ai-agentsconformanceevidence-verificationmcpmodel-context-protocol
Versions collected1
Direct dependencies8From release 0.2.0
Last observed20 Oct, 21:53 UTC

README

Version 0.2.0 documentation

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.

Downloads & popularity

Awaiting observations

No metric observations yet

Download counts and popularity will appear here as the collector receives them.

Versions 1

Collected releases
VersionPublishedDirect dependenciesOpen version
0.2.020 Oct 20268

Package advisories

0
No matching advisories collected

This describes our collected data; it is not a security assessment.

Repository

PENDING
probityai/agent-evidence-mcp

Shared repository data · GitHub

License detected in repository
Not collected

Metadata history

Meaningful changes
Current collected state Current

Observed since 20 Oct, 21:53 UTC

No superseded metadata states collected. Unchanged observations do not create new revisions.

Record identity

package:1ed36550fde4767d1932f5518b3dac9e366c5c6d764f4b431938c2fce1ed411d