MCP.Market

Agent evidence MCP server

by probityai·io.github.probityai/agent-evidence-mcp·v0.2.5

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

A91/100grade A
What users say
No reviews yet
Be the first
Safety scan
A91/100

not scanned yet

Adoption
Growing

0 stars569 downloads/wk

Reviews

Write one

Nobody has reviewed Agent evidence yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Agent evidence tools

No tool declarations could be read from the package source. They show once the server is installed.

Not scanned yet. New listings are scanned within a day or two of arriving.

How Agent evidence compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
91/100
higher than 88% of 4,460 AI and agents servers
Downloads a week
569
more than 88% of 1,538 AI and agents servers with a package

Release history: 4 versions in the registry since 2026-10-20, latest 2026-11-01, typically one every 3 days.

Install Agent evidence in Claude Code, Cursor or VS Code

claude mcp add agent-evidence-mcp -- uvx agent-evidence-mcp
Add to Cursor

What the publisher says

From the Agent evidence repository's README, as published. We do not edit it. Read it on GitHub

agent-evidence-mcp

<!-- mcp-name: io.github.probityai/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==0.2.3. 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 agent-evidence-mcp@0.2.3

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: verifyclaim, verifysample, listvectorcorpora, runvectors, explainvector, lookupterm and checkartifactdigest, canonicalizejson 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

License

Apache-2.0.

Nothing above is checked by us. What we check is on the safety report.

Agent evidence: common questions

Is Agent evidence MCP server safe?
Yes, by our scan: it is graded A (91/100). Read the Agent evidence safety report
How do I install Agent evidence?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Agent evidence need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Agent evidence maintained?
The last commit was 9 days ago (2026-10-26). The latest release is v0.2.5.
What can I use instead of Agent evidence?
Servers from other publishers that do the same job: Watch Skill MCP server, Mockserver MCP server and HOL Guard MCP server.
How does Agent evidence compare with other AI and agents MCP servers?
safety score 91/100 (higher than 88% of 4,460 AI and agents servers); downloads a week 569 (more than 88% of 1,538 AI and agents servers with a package). Full comparison.

Alternatives to Agent evidence

Same job from other publishers: the closest match first, then the best rated.

  • Watch Skill
    Watch video and live sessions, keep timestamped evidence, and verify an agent's own work.
    B
  • Mockserver
    Mock, record/replay, verify and chaos-test any HTTP, REST, gRPC or LLM dependency over MCP.
    A
  • HOL Guard
    Local-first AI agent security evidence and approval workflows through HOL Guard's stdio MCP server.
    A
  • IWE (iwe.md)
    Markdown knowledge base as agent memory. Runs against the notes directory it is started in.
    A
  • OpenWorkProof
    Verifiable agent evidence; opt-in Codex guard and reference SOC alert review.
    A