- Conduid
- Marketplace
- #vllm
MCP servers tagged vllm
87 live MCP servers tagged "vllm", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with vllm.
Geny Executor
Manifest-driven 21-stage agent pipeline for Python — 5 LLM backends (Anthropic / OpenAI / Google / vLLM / Claude Code CLI), tools, skills, memory, sandboxed CLI runs, MCP. The eng…
Hpml Assetopsbench Smart Grid MCP
SmartGridBench: a smart-grid transformer-maintenance benchmark for tool-using LLM agents, built on IBM AssetOpsBench with MCP/direct-call tool surfaces.
Enterprise AI Systems Masterclass From Local First Laptop To Enterprise Cloud In JavaScript
Production-grade AI systems and autonomous agents for fullstack JavaScript/TypeScript engineers. Build air-gapped, local-first architectures with open-weight models, Zod validatio…
Localagents
MCP server that delegates Claude Code agent work to local models (llama.cpp / vLLM) on your own hardware
Magenticbrain Vllm Aspire
Run microsoft/MagenticBrain (14B) locally on GPU via vLLM (Docker), orchestrated with Aspire + the aichatweb RAG template.
RoseChat
AI agent with async, multithreading and mcp support
Inferwatch
Real-time and historical metrics for locally served LLMs (Ollama and vLLM) — dashboard, HTTP API and MCP server. One process, one SQLite file, never in the request path.
Agentic AI Homelab
How I work with agentic AI: personal patterns, homelab infra (vLLM, Ollama, Grafana Alloy, LibreChat), project scaffolding. Not best practices - what I run.
FormicOS
AI kernal/api/ui multi-agent orchestration
Manima
Local-first MCP server that renders (and optionally generates, via Apertus 8B) Manim Community Edition animations — sandboxed, spec-driven, render-only by default.
AI Gateway Hetzner K8s Boilerplate
Flux GitOps boilerplate for a LiteLLM AI gateway on Hetzner Kubernetes — alias routing, MCP RBAC, vLLM inference, dual network paths, and OTel/LGTM hooks.
Qwen3.8 Flash Next Single DGX Spark
Serve Qwen3.8-Flash-Next NVFP4 on a single DGX Spark with TP=1 using this self-contained recipe.
Swarm Context Commander
Inspectable AI agent memory, context engineering and multi-agent orchestration with an MCP server and logical-fleet benchmarks
Kushal9889
Open-source contributions to popular projects: vLLM (90k+ stars) PR #56846 and LlamaIndex (50k+ stars) PR #23053, under review; reported LangChain deepagents (29k+) issue #4846, f…
Small Model Agents
Reliable multi-agent tool calling on a small model, by giving the model less to decide. Tiered routing, schema-validated decisions, graceful tool degradation, MCP server.
Localclaude
Run Claude Code locally on Apple Silicon - Qwen via vllm-mlx fork, web search via SearXNG MCP. One-script install. No cloud, no API keys, no rate limits.
Axolotl Companion
A local-first AI companion with a private LLM on your GPU, MCP tool calling, and an animated 3D axolotl mascot. vLLM + FastAPI + Next.js 15, fully containerised.
Qwen3.5 Fix
A high-performance proxy middleware to fix Qwen3.5 tool calling issues and enable seamless MCP client compatibility.
Dronacharya
Open-source, local-first knowledge management for capturing web pages, notes, bookmarks and documents—then finding and connecting them through hybrid search, RAG, mind maps and to…
NewSift
NewSift is an automated content aggregation and transformation system that processes Telegram channel content into summarized audio formats in multiple languages.
Know Ctl
Transform LinkedIn saved posts into an interactive, interconnected Obsidian knowledge graph. Features a zero-config web dashboard, hybrid LLM routing (Groq + local vLLM/llama.cpp)…
AgentGym
A verifiable Kubernetes incident gym for post-training and serving tool-using agents. Real control plane, deterministic workload simulator, executable rewards.
LLM Inference Lab
Professional open-source LLM inference benchmarking and optimization toolkit: Transformers, vLLM, llama.cpp, quantization analysis, and GPU profiling.
Web Agent
AI-агент, который выполняет задачи в браузере через function calling, и MCP-сервер с инструментами браузера. Работает с OpenAI и self-hosted моделями через vLLM
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Agent Handbook
Illustrated handbook: Agent, MCP, Firecracker, vLLM, SGLang — with diagrams
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.
Houtini Lm
MCP server that saves Claude Code tokens by delegating bounded tasks to local or cloud LLMs. Works with LM Studio, Ollama, vLLM, DeepSeek, Groq, Cerebras.