Freellmpool MCP Server

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 - as a CLI, a Python library, or a local proxy. It can start without credentials when an…

People who work with failover, free llm and gemini and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-04 · ★ 106 · #14 OF 106 MAINTAINED AI & ML · VERIFIED 2026-09-18

MIT · Python servers · how we verify → /methodology

01 · Install Freellmpool

before you install - you'll need

Set ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN, ANTHROPIC_API_KEY, ANTHROPIC_MODEL, ANTHROPIC_SMALL_FAST_MODEL, OPENAI_BASE_URL, OPENAI_API_KEY, GROQ_API_KEY before connecting. FREELLMPOOL_MODE is optional or environment-specific per the README.

Claude Code

claude mcp add 0xzr-freellmpool -- uvx freellmpool

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "0xzr-freellmpool": {
      "command": "uvx",
      "args": [
        "freellmpool"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package freellmpool - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.0xzr is GitHub-verified and matches the repo owner

03 · What Freellmpool can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Limitations (from the README)

- Free-tier models are smaller than frontier models. They're good for drafting, summarizing, classification, triage, and everyday coding - not a replacement for GPT-class reasoning on hard problems. - Quality and capacity vary through the day as high-cap tiers exhaust. freellmpool's local per-day counters reset at UTC midnight; upstream providers use their own limit and reset windows. - Free tiers change without noti

Latest releases

v0.13.0 · 2026-08-30

[0.13.0] - 2026-08-29 · Added · Explicit, bounded discovery and reversible import for Ollama, LM Studio, and · llama.cpp on canonical literal-loopback endpoints. Imported routes are · credential-free, pin-only…

v0.12.3 · 2026-08-29

This release includes the maintenance changes below. Versions 0.12.1 and 0.12.2 · were tagged but not published to PyPI or GitHub Releases. The 0.12.1 container · no-clobber guard correctly stopped an implicit mutable…

v0.12.0 · 2026-08-23

freellmpool 0.12.0 packages the work accumulated since 0.11.4. · Highlights: · 24 cataloged LLM providers, 226 enabled chat routes, and 410 cataloged chat models. · Vercel AI Gateway support with value-focused…

04 · Who maintains Freellmpool

freellmpool is maintained by 0xzr. It's the only MCP server we track from this author; the repo dates to Jun 2026.

05 · Facts

category
AI & ML - ranked #14 of 106 actively-maintained AI & ML servers as of 2026-09-18.
release cadence
3 releases in the last 90 days (latest 2026-08-30)
registry
io.github.0xzr/freellmpool (active, first published 2026-06-17 · 4 versions)
packages
pypi:freellmpool

06 · Freellmpool FAQ

What is 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 - as a CLI, a Python library, or a local proxy. It can start without credentials when an…

Is Freellmpool still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-04 and it shipped 3 releases in the last 90 days. We re-verify nightly.

How do I install Freellmpool?

Run `uvx freellmpool`. The README documents 9 environment variables (ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN, ANTHROPIC_API_KEY…) to set first. Set ANTHROPIC_BASE_URL, ANTHROPIC_AUTH_TOKEN, ANTHROPIC_API_KEY, ANTHROPIC_MODEL, ANTHROPIC_SMALL_FAST_MODEL, OPENAI_BASE_URL, OPENAI_API_KEY, GROQ_API_KEY before connecting. FREELLMPOOL_MODE is optional or environment-specific per the README. You can also paste the ready-made client config above.

Does Freellmpool run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Freellmpool