Quelllm MCP Server

MCP server for quelllm.fr: 190+ open-weights LLM catalog - list, compare, VRAM and cost estimates

Remote serverstreamable-httpPython

What is the Quelllm MCP server?

Most AI and media services work still happens through a UI a human drives. Quelllm MCP server moves it into the conversation instead. MCP server for quelllm.fr: 190+ open-weights LLM catalog - list, compare, VRAM and cost estimates.

The short version

MCP server exposing the quelllm.fr catalog of 190+ open-weights LLMs via Model Context Protocol tools. Use it from Claude Code, Cursor, Continue, or any MCP-compatible client to query models, compare them, estimate VRAM, and compute API vs self-hosted cost.

The tools it exposes

The server publishes 1 tool. What each one is for:

  • Tests — A pytest smoke suite lives under tests/. It covers all 6 tools and the v1.1.0 output invariants, never touches the network (local fixture + mocked

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

How it compares

This sits in the AI and media services group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Quelllm's toolset — Tests — is a fair guide to whether it matches your workflow. It is maintained by MGM-FALCON; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
TestsA pytest smoke suite lives under tests/. It covers all 6 tools and the v1.1.0 output invariants, never touches the network (local fixture + mocked httpx), and stubs the mcp SDK when it isn't importable — so it also runs

How to install the Quelllm MCP server

{
  "mcpServers": {
    "quelllm": {
      "command": "quelllm-mcp"
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Example prompts to try

  • Use Quelllm to Tests.

Frequently asked questions

It connects Quelllm to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (Tests) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Quelllm directly.