freellmpool — Claude Code MCP server: what it does, how to install
Aggregates free and keyless LLM routes into an OpenAI-compatible gateway with automatic fallback. Keeps agent tasks running when rate limits hit.
claude mcp add freellmpool -- uvx freellmpoolWhat freellmpool does
This server pools 23 LLM providers into a single endpoint matching the OpenAI format. It checks free tiers and routes requiring no credentials, such as Pollinations or OVHcloud. When an active model fails or hits quota barriers, the proxy shifts requests to an operational fallback.
The tool provides a proxy on port 8080, daily request tracking, and discovery for local runtimes like Ollama or LM Studio. Crucially, runtime imports reject LAN addresses, binding strictly to loopback destinations like http://127.0.0.1:1234/v1.
Running without Python 3.12 or uv prevents single-command installation.
What it helps with
- route coding prompts through unmetered or free model tiers
- switch to alternate providers automatically during rate limit errors
- bind local desktop engines like Ollama to an OpenAI-compatible proxy
- monitor daily request quotas across multiple external APIs
Example prompts for the agent
- Route this prompt through freellmpool using any active keyless provider.
- Check freellmpool provider health and fall back if the current endpoint fails.
- Start the freellmpool proxy on port 8080 to handle background tasks.
How to install freellmpool
Platform CLI
claude mcp add freellmpool -- uvx freellmpooluvx runs the command named after the package; if the README names another one, use uvx --from freellmpool <command>
Platform CLI
codex mcp add freellmpool -- uvx freellmpooluvx runs the command named after the package; if the README names another one, use uvx --from freellmpool <command>
Config file
{
"mcpServers": {
"freellmpool": {
"command": "uvx",
"args": [
"freellmpool"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from freellmpool <command>
Config file
{
"servers": {
"freellmpool": {
"type": "stdio",
"command": "uvx",
"args": [
"freellmpool"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from freellmpool <command>
Platform CLI
gemini mcp add freellmpool uvx freellmpooluvx runs the command named after the package; if the README names another one, use uvx --from freellmpool <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about freellmpool
How to install freellmpool in Claude Code?
Run claude mcp add freellmpool -- uvx freellmpool in your terminal. You must have uv installed on your machine.
What does freellmpool do?
It aggregates multiple model providers behind a standard OpenAI-style endpoint. When one endpoint stalls or runs out of credits, traffic reroutes to another candidate.
Does freellmpool require API keys?
No, it starts right away using keyless endpoints like Pollinations or Kilo Gateway. You can still supply your own keys to unlock additional models.
