freellmpool
freellmpool is an MCP server that adds messaging tools to AI assistants such as Claude Desktop, Claude Code and Cursor. OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools. It has 120 GitHub stars, is released under the MIT license and runs locally with uvx freellmpool.
- Communication
- MIT
- Actively maintained
Install freellmpool
Generated from the server's MCP registry entry. Replace your-value with your own values.
Claude Desktop
{
"mcpServers": {
"freellmpool": {
"command": "uvx",
"args": [
"freellmpool"
]
}
}
}Settings > Developer > Edit Config. macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\. Restart Claude Desktop afterwards.
Claude Code
claude mcp add --transport stdio freellmpool -- uvx freellmpoolCursor
{
"mcpServers": {
"freellmpool": {
"type": "stdio",
"command": "uvx",
"args": [
"freellmpool"
]
}
}
}Project file; use ~/.cursor/mcp.json to enable it in every project.
VS Code
{
"servers": {
"freellmpool": {
"type": "stdio",
"command": "uvx",
"args": [
"freellmpool"
]
}
}
}Config formats checked against the official docs on Oct 7, 2026: modelcontextprotocol.io (opens in a new tab), code.claude.com (opens in a new tab), cursor.com (opens in a new tab), code.visualstudio.com (opens in a new tab).
About freellmpool
freellmpool catalogs 22 LLM providers as distinct groups spanning recurring free tiers, keyless endpoints, finite trials, pin-only routes, and disabled candidates. It exposes 178 enabled chat routes and 431 cataloged chat models, and automatically pools only enabled routes you can access behind one OpenAI-compatible endpoint โ as a CLI, a Python library, or a local proxy. It can start without credentials when an enabled keyless route is available.
- failover
- free-llm
- gemini
- groq
- llm-gateway
- llm-router
- openai
- openai-proxy
- openrouter
- python
Similar MCP servers
More communication MCP servers
Strata
Klavis-AI/klavis
MCP server for progressive tool usage at any scale (see https://klavis.ai).
OfficialCommunicationPythonVexa
Vexa-ai/vexa
Meeting bot and transcripts for Google Meet, Teams and Zoom.
OfficialCommunicationPythonMCP Server for WinDbg Crash Analysis
svnscha/mcp-windbg
A Model Context Protocol server for Windows crash dump analysis using WinDbg/CDB.
CommunicationPythonRocketmq Rust
mxsm/rocketmq-rust
๐ Apache RocketMQ built in Rust ๐ฆ โ faster, safer, and more memory-efficient.
CommunicationRustWassette
microsoft/wassette
Wassette: A security-oriented runtime that runs WebAssembly Components via MCP.
OfficialCommunicationRustLine Bot MCP Server
line/line-bot-mcp-server
MCP server that integrates the LINE Messaging API to connect an AI Agent to the LINE Official Account.
OfficialCommunicationTypeScript
What is freellmpool?
freellmpool is an MCP server that adds messaging tools to AI assistants such as Claude Desktop, Claude Code and Cursor. OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools. It has 120 GitHub stars, is released under the MIT license and runs locally with uvx freellmpool. The source code is at github.com/0xzr/freellmpool.
How do I install the freellmpool MCP server?
Add the command uvx freellmpool to your MCP client: put it in claude_desktop_config.json for Claude Desktop, run claude mcp add for Claude Code, or add it to .cursor/mcp.json (Cursor) or .vscode/mcp.json (VS Code). The snippets on this page are ready to paste.
Is freellmpool free?
The server is open source under the MIT license, so running it is free. It does not declare any required API key.
Is freellmpool actively maintained?
The most recent commit was on Aug 30, 2026. The latest release is v0.13.0, published Aug 30, 2026. appsgit only lists MCP servers with a commit in the last six months and re-checks every server daily.