MCP servers tagged llm
10K live MCP servers tagged "llm", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with llm.
Local AI Lab
Hands-on course for building local, private AI from scratch - RAG, MCP, LangChain, LangGraph. Runs on your machine (Python, Node.js & C#) with Claude Code, Ollama, Gemini, or Open…
Tsaagan
Human-like browser control for AI agents — verify-first (proves every action worked), with an MCP server + JS & Python SDKs. Playwright + native + extension. MIT.
Conciergent
Turn an OpenAPI spec into an instant messaging chatbot. Conciergent embeds openapi-mcp-gateway to serve the API as MCP tools, or connects any MCP server, with per-user in-chat OAu…
Xbrain
Self-hostable, MCP-native memory backend for teams of humans and AI agents. A FastAPI service enforces a tagging contract (team/project scope, visibility, confidence, truth level,…
Goodeye Docs
Official documentation for Goodeye, which turns the business outcomes you care about into verified AI workflows that agents run reliably.
IANUA Broker
Local-first, offline-by-default security posture scanner for MCP servers and local AI-agent setups (CLI: mcpscan).
Owllm
Local-first AI workstation. Run open-weight models, fine-tune, orchestrate multi-agent teams. No cloud required.
AI Insights
Understand and improve how you use AI coding tools. A local web app that turns raw usage data into a live dashboard — token counts, costs, session history, and configuration healt…
Opengriffin
Self-evolving personal AI agent. Telegram-first. Multi-provider BYO key. Persistent memory, daily journal, skill graph, dream cycle. Free forever. Apache 2.0.
Promptify
A lightweight, self-hosted prompt management system built with Go.
FlowStepMCP
Bridge LLMs to end-users through notifications, confirmations, forms, and progress tracking across multiple platforms
Ghostlab
Local end-to-end testing lab for any MCP server: coding agents role-play real users, drive your tools over multiple turns, score runs, and render/interact with MCP Apps ui:// widg…
Yaggo Brain
FOSS local-first brain / control plane for AI-assisted projects: living memory, code & knowledge graphs, hybrid RAG, cost-aware model routing, a permissioned agent catalog, qualit…
Norma
A native macOS AI assistant that replaces the ChatGPT/Claude ecosystem: chat, a full coding agent, and an orchestrator — running on your own Mac, with your own account.
Blender AI Agent
Local-first AI-to-3D pipeline: LLM planning, validated Blender generation behind an MCP tool boundary, read-only vision review, semantic motion, and GLB/MP4 export with a FastAPI…
Open State
Open-source enterprise Conversation State Orchestration Platform. Deterministic workflow/state engine for LLM-driven conversations — LLM suggests, State Engine decides. MCP + RAG…
XaCodeApp
A powerful AI coding workspace for Windows with multiple models, autonomous tools, team mode, MCP, and vision support.
Mssql MCP Writer
MCP server for SQL Server with read and data modification tools—no DDL operations.
Resonant Archive
Local-first semantic search for your ChatGPT, Claude, and AI conversation history. Python CLI + MCP server for Claude Desktop. Uses sentence-transformers + ChromaDB. No API keys,…
Open Agent Context
Open Agent Context Standard: portable, governed memory and context for AI agents. Python reference implementation with CLI, SQLite, evidence, audit, and MCP adapters.
Langmesh
An open, self-hosted harness for coding agents.
Evidencegene Court
Adversarial autonomous DFIR: Prosecutor/Defender/Arbiter AI court over a typed read-only MCP server. Findings without real evidence refs are structurally rejected. SANS FIND EVIL!…
Planner Guard
A decision-layer guardrail for MCP agents. Gates tool calls by intent and logs the planner's reasoning. Complements MCP firewalls, doesn't replace them.
Terx
Browser-agent memory that turns repeated workflows into deterministic replays.
WindownComputerUse
MCP server giving Claude (and other MCP clients) human-like control of Windows — virtual cursor, OCR, emergency stop, Electron manager. 64 tools.
Mast MCP
Multi-Agent Sequential Thinking — Active validation layer for the MCP sequential-thinking server.
AutoDS Copilot
A no code AI data science copilot. Point it at a spreadsheet and it runs the whole machine learning workflow, then explains the result in plain language. Built with scikit learn,…
Py Agent Framework
Stateful LLM agent framework on pydantic-ai: session persistence, context-window management, and a lifecycle extension system for tools and skills.
Vortexx
Vortex - Ask ocean data a question in plain English. It plans the query, runs it in PostgreSQL, answers with grounded prose and charts - and refuses when the data isn't there.
Molla
Local inference server in pure Mojo. Speaks OpenAI, Anthropic, and MCP. Models are OCI artifacts. Same source runs on CPU, NVIDIA, AMD, and Apple GPUs. Apache-2.0 all the way down.
Secnews
v0.8.1: 面向 AI + 安全从业者的单人本地工作站 · Sentinel Terminal 三层工作流 (Data/Judge/Action) · llm-wiki-2.0 wiki-first 知识库 · CodeGarden 项目全生命周期 · 七 gate 开闸 + 运行时弹性层 + graceful shutdown · MCP 开放 19…
Mooting
Claude Code, Codex and Copilot in one shared council — CLI coding agents debate over MCP, and a human rules every decision. Terminal UI, no API keys.
Nexus Team Agent
Modular AI agent harness on Cloudflare Workers — per-user Durable Objects, shared team DO (OCC notes + single-writer knowledge), streaming Nexus Harness, runtime tool registry, MC…
Fitness Analyst AI
Fitness Analyst AI — Apple Health / HealthKit data pipeline, analysis engine and MCP server. Python owns the truth; the model narrates.
PRAVAL
Progressive Recursive Agentic Vulnerability Assessment Lifecycle — self-hostable agentic AI framework applying continuous LLM reasoning across all 10 phases of enterprise VA with…
LLM Code Security Review MCP
MCP server for running source code security reviews with an LLM
Rag Eval MCP
Touchstone — know if you broke your RAG. An MCP server and CLI that score retrieval quality against a golden set: recall@k, MRR and hit rate, with no LLM calls.
AI For Architect
🚀 24-week AI Engineering journey with Python, LLM APIs, MCP servers & production patterns. Streaming clients, multi-provider CLI, token tracking. Perfect for developers entering A…
Contextverse
Context as a Service. One context for every AI tool. Self-hosted, vendor-neutral, RBAC-ready. 1-minute install.
AI Caller MCP
An MCP (Model Context Protocol) server for AI-powered calling.
Sg AI Dev Tools
Study group resources for AI development tools, focusing on LLMs, GenAI, and Agent architectures including Model Context Protocol (MCP)
Funmcp
MCP（Model Context Protocol）资料收集仓库：汇总 mcphub、smithery、mcp.so 等 MCP 服务器注册站点与中文文档链接，Python 包目前仅有空骨架
Deepcube MCP Server
Open-source Model Context Protocol (MCP) server to query your application telemetry in natural language from VS Code and GitHub Copilot agent mode.
AI Concepts
A dual-language workspace of AI/LLM projects in TypeScript and Python — LangChain, LangGraph, RAG, vector stores, MCP, and more. Includes concept docs, agents, RAG pipelines, and…
ReasonForge
Modular Mathematics Toolkit MCP Server: 111 tools that give LLMs exact math instead of hallucinated guesses. Routes calculations through SymPy/NumPy/SciPy for provably correct res…
Developer Assistant
MCP server with AI-powered code intelligence, OAuth 2.1 security, behavioral anomaly detection, and semantic code search.
Neo4j Yass MCP
Production-ready, security-enhanced MCP server for Neo4j with LLM integration. Transform natural language into graph insights with enterprise-grade security.
Quarkus MCP Server Poc
🔌 A Model Context Protocol server in Java with Quarkus. Built to demo the protocol internals.
Lmcp Demo
MCP (Model Context Protocol) server: tool integration, context management & hallucination-safe AI agent pipelines
Resilio
AI cybersecurity advisor for SMBs - LangGraph ReAct agent with RAG over NIST CSF / SP 800-53 / CIS Controls v8, MCP HTTP server, Langfuse tracing, RAGAS eval.