local-llm
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@local-llmAsk the local model to summarize this changelog for a non-technical audience."
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
local-llm
Deux façons de faire travailler un LLM local (Qwen3.6-35B-A3B-AWQ servi par vLLM sur une Jetson AGX Orin) à la place de Claude, pour les sous-tâches mécaniques ou volumineuses.
Fichier | Rôle |
| Serveur MCP exposant l'outil |
| CLI qui lit les fichiers elle-même — rien du contenu ne transite par le contexte de Claude |
La distinction compte : passer par l'outil MCP oblige Claude à recopier le contenu dans
l'argument prompt, ce qui coûte plus cher en tokens de sortie que de ne rien déléguer.
delegate.py évite ça — Claude ne voit que le résultat.
Installation
python3 -m venv .venv
.venv/bin/pip install -r requirements.txtRelated MCP server: cn-llm-mcp
delegate.py
.venv/bin/python delegate.py --file '<fichier_ou_glob>' --task "<instruction>" [--out <sortie>]--file est répétable et accepte les globs. Options : --system, --max-tokens
(2048), --temperature (0.3), --think (raisonnement interne, plus lent), --out.
server.py (MCP)
Déclaration dans .mcp.json :
{
"mcpServers": {
"local-llm": {
"command": "/chemin/vers/.venv/bin/python",
"args": ["/chemin/vers/server.py"],
"env": {
"VLLM_URL": "http://localhost:8000/v1/chat/completions",
"VLLM_MODEL": "cyankiwi/Qwen3.6-35B-A3B-AWQ-4bit"
}
}
}
}Configuration
Tout passe par l'environnement, rien n'est codé en dur :
VLLM_URL— défauthttp://localhost:8000/v1/chat/completionsVLLM_MODEL— défautcyankiwi/Qwen3.6-35B-A3B-AWQ-4bit
Timeout des requêtes : 900 s (génération longue sur Jetson).
Bon à savoir
Le modèle local est plus petit et moins fiable : ses sorties sont des brouillons à relire, pas des vérités. À éviter pour les décisions d'architecture et le code sensible (sécurité, auth, paiement).
Testé avec Python 3.10, httpx 0.28.1, mcp 1.9.4.
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Connectors
Pay-per-call GLM 5.3 MCP tool via x402 on Base. Reasoning, tool-calls, OpenAI-compatible.
Stateless agentic tools over MCP: concept extraction, long-context, knowledge graph, planning.
OCR, transcription, file extraction, and image generation for AI agents via MCP.
OpenAI-compatible LLM MCP (7 tools); chat via balance key or x402 USDC on Base
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceConnects local LLMs to external tools (calculator, knowledge base) via MCP protocol, enabling automatic tool detection and execution to enhance query responses.MIT
- FlicenseAqualityCmaintenanceLocal MCP server that enables delegating low-risk tasks like summarization or code patches to a low-cost model, with the main agent reviewing results.2
- AlicenseAqualityBmaintenanceEnables AI agents to offload mechanical, high-token work to local Ollama models through MCP, with role-based model discovery, batch processing, and file-aware inputs.4MIT
- FlicenseNot gradedqualityBmaintenanceMCP server that enables an agent to spawn sub-agents (a crew) via a local tool, allowing delegation of large tasks to parallel workers with a human approval gate and efficient token usage.
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/avtplay/mcp-servers-local-llm'
If you have feedback or need assistance with the MCP directory API, please join our Discord server