mcpField
A
Agent evidence

Agent evidence

Local
github.com/probityaiDeveloper Tools0Updated today
Repository

About Agent evidence

An offline, read-only MCP server for checking claims about AI systems against supplied evidence and replaying conformance vectors. It is intended for agent builders, auditors, and platform engineers, and performs checks without fetching, writing, or sending data.

Key features

  1. 01Verify claims against supplied evidence
  2. 02Run and inspect conformance vectors
  3. 03Look up vocabulary terms
  4. 04Check artifact digests and DSSE
  5. 05Canonicalize JSON

Use cases

  1. 01Auditing AI-system claims against source captures
  2. 02Replaying conformance checks during development
  3. 03Checking signed artifacts and JSON records

MCP support

Exposes nine bounded, read-only tools to MCP clients for evidence verification, conformance vectors, vocabulary lookup, digest checking, JSON canonicalization, and DSSE verification. All checks run offline.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "probityai-agent-evidence": {
      "command": "uvx",
      "args": [
        "agent-evidence-mcp"
      ]
    }
  }
}
Run commanduvx agent-evidence-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
pypiagent-evidence-mcp0.2.4

Tools

9

Saved tool list · updated today

ParameterTypeRequiredDescription
caseobjectYes
policyobjectYes
artifactsanyNo

Details

From the project README

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.

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==0.2.3. 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 [email protected]

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==0.2.3 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 0.2.3. 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.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.