freellmpool MCP Server

by 0xzr Your server? Claim it

local only

freellmpool runs on your own machine — the client starts it, so there is no endpoint to ping. 966 installs a week from pypi. Last commit 8 Oct 2026.

OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.

Installs per day peak 232 · avg 102 · +17% w/w

a month agotoday

966

Installs / week

pypi · freellmpool

143

Stars

3 open issues

8 Oct 2026

Last commit

from GitHub

MIT

License

Python

What the code does

We read the source, 2 d ago · rules 995398eba69f

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/freellmpool/tailnet.py:97, [пакет] src/freellmpool/tailnet.py:97

    return subprocess.run(

Dumps the whole environment src/freellmpool/router.py:266, [пакет] src/freellmpool/router.py:266

        self.env = env if env is not None else dict(os.environ)

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

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

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 freellmpool -- uvx freellmpool

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

{
  "mcpServers": {
    "freellmpool": {
      "command": "uvx",
      "args": [
        "freellmpool"
      ]
    }
  }
}

~/.codex/config.toml

[mcp_servers.freellmpool]
command = "uvx"
args = ["freellmpool"]

.cursor/mcp.json

{
  "mcpServers": {
    "freellmpool": {
      "command": "uvx",
      "args": [
        "freellmpool"
      ]
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "freellmpool": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "freellmpool"
      ]
    }
  }
}

Alternatives to freellmpool

same job, measured the same way

Bay Run

by barneywohl

Free OpenAI-compatible inference with signed provenance receipts and 3 focused MCP tools.

3 tools answering

Routara LLM Gateway

by 36412749-collab

OpenAI-compatible LLM, image and video APIs via Routara (api.routara.ai).

41 installs/wk local only

Qwen38 Free Gateway

by khs0927

Free Qwen3.8-27B gateway with isolated Minis provider, SSE, retry/failover, and MCP.

7 tools answering

treg.to

by superdesigndev

OpenRouter for tools and data. Compare catalog providers and call them from one hosted MCP endpoint.

answering

Qsp Client

by qso-graph

QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)

1 326 installs/wk local only

Proxyllm MCP

by proxyllm

OpenAI-compatible LLM gateway: models, savings math, key provisioning, autonomous email-OTP signup

119 installs/wk local only

DDG Agent Services

by daedalusdevelopmentgroup

Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.

389 installs/wk 54 tools answering

DDG Agent Services

by daedalusdevelopmentgroup

Pay-per-call x402 gateway: agent tools, OpenAI-compatible LLM, market data, RPC, security audits.

local only

freellmpool — questions

Answers built from our own checks of this server.

Why is there no uptime for freellmpool?

freellmpool 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 freellmpool was installed 966 times last week.

How do I connect freellmpool?

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 freellmpool straight from pypi; nothing to host, nothing to sign up for.

How many people use freellmpool?

The pypi package freellmpool was installed 966 times in the last week. Week over week that is +17%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is freellmpool open source?

Yes — it is published under the MIT licence, written in Python, 143 stars on GitHub and 3 open issues. The source link is on this page, so you can read exactly what it does with your data before you connect it.