Agent evidence MCP Server

by probityai Your server? Claim it

local only

Agent evidence runs on your own machine — the client starts it, so there is no endpoint to ping. 799 installs a week from pypi. Last commit 20 Oct 2026.

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

Installs per day peak 577 · avg 26

a month agotoday

799

Installs / week

pypi · agent-evidence-mcp

Stars

0 open issues

20 Oct 2026

Last commit

from GitHub

Apache-2.0

License

Python

What the code does

We read the source, 4 d ago · rules 995398eba69f

Evidence

Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.

Claims read-only, but the code runs commands src/agent_evidence_mcp/tools.py:106, [пакет] src/agent_evidence_mcp/tools.py:106

    return subprocess.run(

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command src/agent_evidence_mcp/tools.py:106, [пакет] src/agent_evidence_mcp/tools.py:106

    return subprocess.run(

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

We found things in this code

Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch Agent evidence and you get told the day something new turns up.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agent-evidence-mcp -- uvx agent-evidence-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "agent-evidence-mcp": {
      "command": "uvx",
      "args": [
        "agent-evidence-mcp"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.agent-evidence-mcp]
command = "uvx"
args = ["agent-evidence-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "agent-evidence-mcp": {
      "command": "uvx",
      "args": [
        "agent-evidence-mcp"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agent-evidence-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "agent-evidence-mcp"
      ]
    }
  }
}

Alternatives to Agent evidence

same job, measured the same way

Achromat MOM

by achromat

Recall and calibrate agent tool calls against verified policy lessons from Achromat MOM.

270 installs/wk 1 tools answering

MCP Qdrant

by infoinlet-marketplace

Read-only Qdrant vector DB for AI agents — collections, info, browse points, count, search.

16 installs/wk local only

SAME - Stateless Agent Memory Engine

by sgx-labs

Persistent memory for AI coding agents. Local-first SQLite + vector search. 17 MCP tools.

44 installs/wk local only

VelesDB Memory

by cyberlife-coder

Offline agentic memory: remember/recall/relate/forget/why over a fused vector+graph+columnar engine

local only

Changegamer

by beneb89

Agent-first resource directory for AI agents: protocols, security, RAG, memory, evals, and more.

14 tools answering

amu-pgvector

by sangaraju1988

Lineage-gated agent memory tools on Postgres + pgvector, enforced by row-level security.

136 installs/wk local only

Citadel

by citadeldb

Encrypted-first embedded database with vector search and agent memory, exposed as MCP tools

499 installs/wk local only

Telys — on-device memory

by thyn-ai

Private on-device memory & retrieval for AI assistants — offline vector + lexical search.

304 installs/wk local only

Agent evidence — questions

Answers built from our own checks of this server.

Why is there no uptime for Agent evidence?

Agent evidence runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package agent-evidence-mcp was installed 799 times last week.

How do I connect Agent evidence?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It runs locally, so the command pulls agent-evidence-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use Agent evidence?

The pypi package agent-evidence-mcp was installed 799 times in the last week. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is Agent evidence open source?

Yes — it is published under the Apache-2.0 licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.