Local AI MCP
Run, fit, and route work to local LLMs (Ollama, LM Studio, llama.cpp, MLX, vLLM, and more).
Serveur MCP · par TMHSDigital
Aperçu
Local AI MCP est un serveur MCP publié par TMHSDigital. Places de marché que nous lisons et qui le référencent : 1 (Official MCP Registry). Le dernier changement enregistré date du 2026-11-03. Selon notre passage sur les places de marché du 2026-11-13.
Ce qu'il demande
- S'exécute sur votre machine
- Secrets : 3
- Paramètres : 17
Demande: MOONSHOT_API_KEY (secrète), OPENAI_COMPAT_API_KEY (secrète), VLLM_API_KEY (secrète)
Ce qu'il déclare, demande et exécute, en détail
N’installez que des plugins de développeurs en qui vous avez confiance. Nous reprenons ce que publient les places de marché et ne testons pas les plugins.
Fonctionne avec
- Claude Code
- Codex
- Cursor
- VS Code
- Copilot CLI
D'après les marketplaces qui le listent et le transport MCP qu'il déclare, tels que chaque client les documente. Nous ne testons pas les plugins.
Connecter
Commandes et configurations construites uniquement à partir de ce que déclarent ses places de marché. Nous ne les exécutons pas pour vous et ne testons pas les plugins.
En serveur MCP local : paquet npm
Construit à partir de ce que déclare Official MCP Registry.
claude mcp add --env "MOONSHOT_API_KEY=<YOUR_MOONSHOT_API_KEY>" --env "OPENAI_COMPAT_API_KEY=<YOUR_OPENAI_COMPAT_API_KEY>" --env "VLLM_API_KEY=<YOUR_VLLM_API_KEY>" --transport stdio local-ai-mcp -- npx -y @tmhs/local-ai-mcp[mcp_servers.local-ai-mcp]
command = "npx"
args = ["-y", "@tmhs/local-ai-mcp"]
[mcp_servers.local-ai-mcp.env]
MOONSHOT_API_KEY = "<YOUR_MOONSHOT_API_KEY>"
OPENAI_COMPAT_API_KEY = "<YOUR_OPENAI_COMPAT_API_KEY>"
VLLM_API_KEY = "<YOUR_VLLM_API_KEY>"{
"mcpServers": {
"local-ai-mcp": {
"command": "npx",
"args": [
"-y",
"@tmhs/local-ai-mcp"
],
"env": {
"MOONSHOT_API_KEY": "<YOUR_MOONSHOT_API_KEY>",
"OPENAI_COMPAT_API_KEY": "<YOUR_OPENAI_COMPAT_API_KEY>",
"VLLM_API_KEY": "<YOUR_VLLM_API_KEY>"
}
}
}
}Remplacez les valeurs entre chevrons par les vôtres. Nous montrons les noms des paramètres, jamais de valeurs.
Paramètres facultatifs qu’il indique aussi : DOCKER_MODEL_RUNNER_HOST, FOUNDRY_LOCAL_HOST, LLAMACPP_HOST, LMSTUDIO_HOST, LOCAL_AI_ALLOW_HOSTED_FALLBACK, LOCAL_AI_BENCHMARK_CACHE, LOCAL_AI_DISABLE, LOCAL_AI_DISABLE_NETWORK_SEARCH, LOCAL_AI_PROVIDERS, MLX_HOST, MOONSHOT_HOST, OLLAMA_HOST, OPENAI_COMPAT_HOST, VLLM_HOST.
Où il est publié
| Place de marché | Statut | Version | Chiffres | Vérifié | Vu pour la première fois |
|---|---|---|---|---|---|
| Official MCP Registry (Ouvrir la fiche du registre) | Référencé | 0.6.1 | Forks (GitHub): 0 Étoiles (GitHub): 0 |
Non marqué |
Chaque chiffre est celui de la place de marché et n'est jamais additionné entre places de marché. Une place de marché qui ne publie pas de chiffre n'en affiche aucun : pas de nombre ne veut pas dire zéro.
Ce qui a changé
- Official MCP Registry: version 0.6.1 publiée (avant 0.6.0)
- Est devenu un produit que nous suivons
- Official MCP Registry: apparu
Plugins similaires
Produits dont les noms, descriptions, outils et skills sont les plus proches de celui-ci par le sens, sur toutes les places de marché que nous lisons. La proximité n'est classée qu'à l'intérieur de cette liste.
-
lm io.github.houtini-ai/lm
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
-
Call your local Ollama or vLLM model over MCP with schema-validated JSON output
-
ollama-handoff io.github.Michael-WhiteCapData/ollama-handoff
Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
-
Let a planning agent hand bounded language work to a local Ollama model.
-
Wraps local Ollama models so bulk generation runs on your own hardware, not a paid API.
-
qsp-mcp io.github.qso-graph/qsp-mcp
QSP — relay MCP tools to any OpenAI-compatible local LLM (llama.cpp, Ollama, vLLM)
-
MCP Client for Ollama - A client for connecting to Model Context Protocol servers using Ollama
-
MCP server providing access to 300+ AI models via OpenRouter
-
rubber-duck io.github.nesquikm/rubber-duck
Bridge to multiple LLMs and CLI agents: councils, debates, voting, and more
-
llmtest-mcp io.github.tjacquesson/llmtest-mcp
Benchmark AI models on real prompts. Find cheaper, faster alternatives across 340+ models.
Plugins similaires par place de marché
La même question posée à chaque place de marché séparément : y a-t-il là un équivalent de ce plugin ?
Référencé sur Claude Code: claude-plugins-community (5)
-
Multi-LLM orchestration MCP server. Delegate tasks to Claude Code, Codex, and Gemini CLIs with session management, retry logic, async job orchestration, and token optimization.
-
Claude model selection advisor — recommends optimal model for each task via shell hook. Zero attack surface.
-
eu-ai-act-compliance-mcp io.github.CSOAI-ORG/eu-ai-act-compliance-mcp
Eu Ai Act Compliance MCP Server by MEOK AI Labs
-
agent-discover io.github.keshrath/agent-discover
Find, install and enable MCP servers mid-session on any host, with consent and tool pinning
-
Search, browse, and install MCP servers, agents, skills, prompts, and plugins from the conduitAI catalog — directly from Claude Code.
Référencé sur Claude Code: claude-plugins-official (5)
-
Agent Skills for Together AI platform — inference, training, embeddings, audio, video, images, function calling, and infrastructure. Covers serverless chat completions…
-
AMD's verified Agent Skills in one plugin: route image/audio through local AI on Ryzen AI, serve LLMs on AMD Instinct GPUs with vLLM, optimize inference throughput with Hyperloom…
-
Build, train, evaluate, and use open source AI models, datasets, and spaces.
-
Build, train, and deploy AI models with deep AWS AI/ML expertise brought directly into your coding assistants, covering the surface area of Amazon SageMaker AI.
-
Find the right NVIDIA skill for GPU acceleration, CUDA, AI agents, data loading, training, inference, robotics, Physical AI, Omniverse, simulation, and other NVIDIA-powered…
Référencé sur Claude: knowledge-work-plugins (5)
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
Skills for working with Langfuse, the open-source LLM engineering platform for tracing, prompt management, and evaluation.
-
DataRobot skills for AI/ML workflows — model training, deployment, predictions, feature engineering, monitoring, explainability, data preparation, App Framework CI/CD, and…
-
Sanity content platform integration with MCP server, agent skills, and slash commands. Query and author content, build and optimize GROQ queries, design schemas, and set up Visual…
-
MCP server for terminal commands, file operations, and process management
Référencé sur Codex: openai-curated (openai/plugins) (5)
-
Skills for NVIDIAs ecosystem spans GPU acceleration, CUDA, AI agents, inference, robotics, Physical AI, Omniverse, and simulation. This plugin helps you understand the pieces…
-
Build with OpenAI APIs, Agents SDK, and ChatGPT Apps, and create and save OpenAI API keys from Codex.
-
Evaluate Codex skills and plugins from chat with a beginner-friendly start command, local-first reports, token budget explanations, and guided benchmarking.
-
Cloudflare platform plugin with curated skills for Workers, Wrangler, and Agents SDK plus the official Cloudflare API MCP server.
-
Install, open, and connect the signed ChatCut Desktop app from Codex.
Référencé sur Community GitHub marketplaces (5)
-
Build Gemini- and ChatGPT-style apps, assistants with memory, RAG over vector databases and multi-provider AI features in JavaScript with the IntelliNode library, plus an MCP…
-
Build high-quality MCP servers for LLM integrations
-
mcp-builder-anthropic
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when building MCP servers…
-
Skills for deploying and benchmarking vLLM with Claude Code
-
comfyui-mcp io.github.artokun/comfyui-mcp
MCP server + Claude Code plugin for ComfyUI: run workflows, generate images, manage models & VRAM.
Référencé sur Copilot CLI: github/awesome-copilot (5)
-
Run a lightweight, role-separated AI development team with flexible tools, developer-selected models, proportionate planning, and optional QA.
-
Multi-model council for Copilot CLI: three subagents on different model families (Anthropic, OpenAI, Google) answer independently, then build on each other or attack the leading…
-
Complete toolkit for building Model Context Protocol (MCP) servers in Go using the official github.com/modelcontextprotocol/go-sdk. Includes instructions for best practices, a…
-
Figma design platform integration. Access design files, extract component information, read design tokens, and translate designs into code. Bridge the gap between design and…
-
Transform Claude into an Azure expert. This plugin integrates the Azure MCP server and specialized Azure skills to move beyond generic advice. It enables Claude to perform…
Référencé sur Copilot CLI: github/copilot-plugins (5)
-
Toolkit for building Microsoft 365 Copilot declarative agents — scaffolding, JSON manifest development, and capability configuration.
-
model-apps
Build and deploy Power Apps generative pages for model-driven apps with specialist agents for planning, entity creation, and parallel code generation. Requires PAC CLI >= 2.7.0…
-
mcp-apps
Generate MCP App widgets for MCP tools. Produces self-contained HTML widgets using the MCP Apps protocol.
-
Build Power Apps Canvas Apps using the Canvas Authoring MCP server.
-
Complete bundle: all Microsoft Skills for Fabric for developers and consumers.
Référencé sur Cursor: cursor/plugins (5)
-
Iterative self-referential AI loops using the Ralph Wiggum technique.
-
Let Grok Bot reach MCP servers on your private Tailscale network: connect your own tailnet, or your team's company tailnets turned on by a team admin, with each member using their…
-
Fan large tasks out across parallel cloud agents with planners, workers, verifiers, and structured handoffs.
-
Incremental transcript-driven memory updates for AGENTS.md using high-signal bullet points only.
-
Build apps, scripts, and automations with the TypeScript SDK.
Référencé sur Docker MCP Catalog (5)
-
Read and score Opik traces, experiments, datasets and prompts from your AI assistant.
-
A universal MCP (Model Context Protocol) server to integrate any API with Claude Desktop using only Docker configurations.
-
Give your AI agents trusted access to the full Postman platform.
-
Bridges multiple AI models and CLIs, enabling orchestrated workflows across Claude Code, Gemini CLI, Codex CLI, and other AI development tools.
-
Bridges n8n's workflow automation platform with AI models, providing access to 543 n8n nodes, workflow templates, and AI-capable automation tools.
Référencé sur Official MCP Registry (5)
-
lm io.github.houtini-ai/lm
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
-
Call your local Ollama or vLLM model over MCP with schema-validated JSON output
-
ollama-handoff io.github.Michael-WhiteCapData/ollama-handoff
Offload cheap work from your AI agent to a local Ollama model, at zero cloud cost.
-
Let a planning agent hand bounded language work to a local Ollama model.
-
Wraps local Ollama models so bulk generation runs on your own hardware, not a paid API.
Référencé sur PyPI (MCP servers) (5)
-
MCP Client for Ollama - A client for connecting to Model Context Protocol servers using Ollama
-
mcp-openai io.github.AceDataCloud/mcp-openai
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
-
offline-mcp io.github.gabrielmahia/offline-mcp
Local AI over Ollama for low connectivity: status, local inference, model and deployment guides.
-
local-delegate io.github.ZahiriNatZuke/local-delegate
Delegate mechanical text tasks to a local OpenAI-compatible LLM to save Claude quota.
-
Automatic MCP Server & OpenAI Tools Bridge for apcore
Référencé sur npm registry (MCP servers) (5)
-
lm io.github.houtini-ai/lm
Connect Claude to any OpenAI-compatible LLM endpoint and offload routine work to a local model.
-
rubber-duck io.github.nesquikm/rubber-duck
Bridge to multiple LLMs and CLI agents: councils, debates, voting, and more
-
Chat, image, video, speech, music and media models with one account — local (npx) or hosted.
-
Automatic MCP Server & OpenAI Tools Bridge for apcore
-
Run Claude Code with any model - OpenRouter, Ollama, LM Studio & local models
Trouvés par le sens, et non par un code ou un dépôt commun : les plugins similaires restent des produits distincts, et ceci n'est ni un avis ni une recommandation.
Vous voulez cette marque pour votre plugin dans notre catalogue ?
Prouvez que vous le maintenez avec un fichier dans son dépôt, un fichier sur votre domaine ou un enregistrement DNS, et vous pourrez afficher cette marque sur la fiche, avec des bannières à jour pour votre site et votre README. Comment se passe la vérification
Vous recevez aussi des alertes quand une marketplace le publie, le retire, change sa marque vérifiée ou ce qu'il demande, et son endpoint distant est surveillé comme un service web.
Données issues de Official MCP Registry. Les chiffres proviennent de nos propres passages réguliers sur les places de marché, dernière lecture le . Nous ne publions aucune coordonnée des éditeurs de plugins.