# freellmpool

Aggregates free and keyless LLM routes into an OpenAI-compatible gateway with automatic fallback. Keeps agent tasks running when rate limits hit.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI · ★ 134
- Author: 0xzr
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/0xzr/freellmpool
- Updated: 2026-10-23
- HTML: https://affpapa.org/en/nevibecode/mcp/freellmpool

## What it 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.

## Requirements
- Needs: Python and uv (commands run via uvx)

## Install

### Claude Code (native platform)

**Platform CLI**
```bash
claude mcp add freellmpool -- uvx freellmpool
```
uvx runs the command named after the package; if the README names another one, use uvx --from freellmpool <command>

### Codex

**Platform CLI**
```bash
codex mcp add freellmpool -- uvx freellmpool
```
uvx runs the command named after the package; if the README names another one, use uvx --from freellmpool <command>

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "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>

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "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>

### Gemini CLI

**Platform CLI**
```bash
gemini mcp add freellmpool uvx freellmpool
```
uvx runs the command named after the package; if the README names another one, use uvx --from freellmpool <command>

## When to use it
- 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
- 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.

## Similar
- [MCP Toolbox for Databases](https://affpapa.org/en/nevibecode/mcp/googleapis-mcp-toolbox-for-databases.md) — MCP server · ★ 16717
- [labelhead-artist-momentum](https://affpapa.org/en/nevibecode/mcp/labelhead-artist-momentum.md) — MCP server · ★ 107423
- [Agent Skills Search Server](https://affpapa.org/en/nevibecode/mcp/agent-skills-search-server.md) — MCP server · ★ 26559
- [Skyvern](https://affpapa.org/en/nevibecode/mcp/skyvern.md) — MCP server · ★ 23263
- [Nhost](https://affpapa.org/en/nevibecode/mcp/nhost.md) — MCP server · ★ 9366
- [PraisonAI](https://affpapa.org/en/nevibecode/mcp/praisonai.md) — MCP server · ★ 9289

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md