Proven MCP Server

by malikabyl Your server? Claim it

local only

Proven runs on your own machine — the client starts it, so there is no endpoint to ping. 741 installs a week from pypi. Last commit 3 Nov 2026.

Judge AI-written Python: no invented packages or calls, no facts from memory, verified LLM output.

Installs per day peak 559 · avg 24

a month agotoday

741

Installs / week

pypi · proven-judge

Stars

0 open issues

3 Nov 2026

Last commit

from GitHub

MIT

License

Python

Nothing serious here today

Today is the operative word: we check Proven every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

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 proven -- uvx proven-judge

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

{
  "mcpServers": {
    "proven": {
      "command": "uvx",
      "args": [
        "proven-judge"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.proven]
command = "uvx"
args = ["proven-judge"]

.cursor/mcp.json

{
  "mcpServers": {
    "proven": {
      "command": "uvx",
      "args": [
        "proven-judge"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "proven": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "proven-judge"
      ]
    }
  }
}

Alternatives to Proven

same job, measured the same way

ViBo Memory

by vnbochkarev-netizen

Local-first memory for AI agents: facts with hash-chain provenance, verified recall.

local only

Al Buddy Memory

by flytomoon

Governed local memory for AI agents: facts are retired, not overwritten, and every call is audited.

114 installs/wk local only

Gather

by hunta-ai

Attestable memory for AI agents: curated writes, verifiable tenant isolation, bi-temporal facts.

answering

Echo Memory

by echo-mem

Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.

558 installs/wk answering

Echo Memory

by ayushcodes10

Shared memory for AI agents, as a graph in your own Postgres. Writes never call an LLM.

answering

DialValet

by dialvalet

U.S. outbound calls from a verified caller ID for AI agents via CLI/MCP.

answering

Hosaka

by plus8bit

Company facts for AI agents: which vendors a company uses, proven from DNS. Paid in USDC.

61 installs/wk local only

Toon Memory

by luiggival08

Offline persistent memory for AI coding agents — 35 tools, 80% fewer calls, no LLM

98 installs/wk local only

Proven — questions

Answers built from our own checks of this server.

Why is there no uptime for Proven?

Proven 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 proven-judge was installed 741 times last week.

How do I connect Proven?

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 proven-judge straight from pypi; nothing to host, nothing to sign up for.

How many people use Proven?

The pypi package proven-judge was installed 741 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 Proven open source?

Yes — it is published under the MIT licence, written in Python and 1 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.