MGM-FALCON/quelllm-mcp

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.
Tools exposed
| Tool | Description |
|---|---|
| list_models(filter_origin?, filter_family?, max_params_b?) | List models with filters (origin code, family, max params in B) |
| get_model(model_id) | Full record for one model (params, vram per quant, context window, family, tags, license, URLs) |
| compare(model_a_id, model_b_id) | Side-by-side comparison with verdict |
| estimate_vram(model_id, quant) | VRAM in GB at chosen quant + recommended GPU/Mac tiers |
| estimate_cost(input_tokens_per_month, output_tokens_per_month, ...) | Cost in EUR — full table API providers vs self-hosted hardware OR a specific id |
| search_models(query, limit?) | Fuzzy search by name, family, tag, author |
Install
Install from source (not yet on PyPI) :
Or run without installing, using uv :
For local development :
Use with Claude Code
Add to ~/.claude.json or a project's .mcp.json. If you installed with pip :
Or zero-install with uvx :
Use with Claude Desktop
Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) :
Use with Cursor / Continue / Cline
Most MCP clients accept the same JSON config :
Example queries (from your client)
Data source
All data pulled from **quelllm.fr/api/** (CC BY 4.0, no key, CORS-enabled). Cached locally for 1h to avoid rate-limiting.
API pricing data (GPT-5, Claude Opus 4.7, Gemini 2.5, DeepSeek, Mistral) and hardware pricing (RTX 50-series, Mac M4) are hardcoded as of **2026-05** — verify semestrially.
Model-selection guides by language
The MCP server exposes the same catalog to any compatible client. These companion guides explain model selection, memory trade-offs and repeatable evaluation tasks for different languages. They are source-based guides, not new hardware benchmarks.
| Language | Guide |
| --- | --- |
| Français | IA française en local : choisir un modèle Ministral |
| English | Local AI for English: how to choose Gemma, Qwen or Ministral |
| Deutsch | Deutsche KI lokal nutzen: Teuken und Apertus im Vergleich |
| Italiano | Intelligenza artificiale italiana in locale: Minerva e Velvet |
| Español | IA española en local: cómo elegir entre Salamandra y ALIA |
| Português brasileiro | IA em português no computador: como escolher um modelo Tucano2 |