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.
Agt
Local-first multi-agent orchestration. Tell a lead agent a goal: it writes the prompts, creates the agents and MCP tools, and runs the work in a group chat.
Lycosa
Lycosa — Open-source AI agent orchestration platform for building, coordinating, and deploying multi-agent LLM systems with RAG, MCP, knowledge bases, and automated workflows.
LLM Engineering Program
Open-source, bilingual LLM engineering course with hands-on labs for RAG, AI agents, MCP, evals, harnesses, loops and production.
NexusMind
Local-first Agentic RAG engine - GraphRAG, hybrid retrieval (BM25 + dense + RRF + rerank), multi-agent orchestration, MCP-native, 100% local inference via Ollama.
Clojure AI
A micro-guide to using AI tools to support a Clojure Workflow
R Assistant Tool
Chat-based CSV data economic analysis using AI-generated R code with visualization and MCP integration
Python SDK
Integrate the Assinafy API into your Python applications to manage electronic signatures, documents, and webhooks with a synchronous client.
Agent Mesh
Production-ready multi-agent orchestrator — confidence-gated routing with a pluggable classifier, MCP or in-process agent dispatch, per-agent circuit breakers, and pluggable sessi…
Contexture
My personal setup for working with AI; what I learned from existing plugins, plus a bunch of my own, built the way I like to work.
Octantis
Intelligent infrastructure monitoring agent. Receives OTLP metrics/logs, uses an LLM to autonomously investigate and classify incidents via MCP, and notifies Slack/Discord with a…
ElGraph
Graph-first agent framework on the BEAM (Elixir/OTP) — durable execution, HITL, time-travel, checkpoints, MCP. A LangGraph alternative, no Python.
Adjutant
Your AI chief of staff for every product you're building.
Mux
Local-first coding router with MCP tools and CLI SOTA handoff (Codex, Claude, Gemini).
YAML Multi Agent Orchestrator
🤖 Define and execute multi-agent AI workflows declaratively using YAML, simplifying orchestration and enhancing collaboration through automatic context handling.
Hrafn
Lightweight, modular AI agent runtime — thinks (Hrafn) and remembers (MuninnDB) 🐦⬛
Cakeagent
Minimal, secure personal AI agent — Claude Agent SDK + Telegram + MCP
Melo
Local-first AI workspace for macOS, iPhone and Android, with Claude, OpenAI, OpenRouter and compatible local models. Projects, memory and collaborative Agents.
Agent Firewall
A dry-run firewall for coding agents — approve & audit tool/MCP/shell calls before they hit the real world. By Martello Systems.
Cortex
Self-hosted desktop app for driving multiple AI coding agents - CLI, API, and local models - from one window.
Claude Code Config
Opinionated Claude Code config: path-scoped rules, 34 skills, 12 subagents, deterministic hooks, and a multi-agent PR review. Stack-agnostic; run /adapt-to-project to fit any repo.
CO WPSppt
CO-WPSppt — WPS 演示 COM 自动化（OpenClaw / run-spec / Cursor 扩展）
Bus MCP
MCP server exposing a Raspberry Pi's CAN / RS485 / UART / I2C / SPI / GPIO buses to AI agents (Claude Desktop, Claude Code, ...)
Gram One
Lightweight modular AI assistant platform with multi-provider LLM support, MCP integration, RAG-powered fact memory, profiles, chat persistence, and live token tracking.
PIA
🩺 Chest pain triage (Manchester Protocol, Yellow-Blue) with multi-agent architecture, local LLMs, RAG, and ML.
Agent Workflow
Agent flow — AI harness system: thiết kế pipeline agent, chạy task qua runner, theo dõi HITL gate và artifact trên dashboard local-first
Cama
Circular Associative Memory Architecture — an emotionally-indexed, three-layer memory system for human-AI interaction continuity
Glyphdown
Lossless, on-device token-cost reduction for Claude Code and LLM coding agents. Free plugin: compresses tool-result output, dedups context, compacts the system prompt — stacks on…
Deepseek Claude Code Starter
DeepSeek V4 inside Claude Code — the scaffold that started my AI systems work. 9 agents, security hooks, MIT.
Prompt A Porter
Libreria locale-first per prompt AI — vault cifrato, ricerca semantica offline, MCP-ready, AGPL 3.0
Scrape Website
Incredibly High Performant web scraper (seconds for what takes others lots of minutes) - battle tested on millions of websites
Orchester
Open-source platform for building teams of AI agents — orchestrator delegates, specialists execute, persistent memory learns. Multi-tenant, self-hostable on Postgres. 80+ AI provi…
Markgrab
Universal web content extraction — any URL to LLM-ready markdown
Crow
Bayesian change-trust layer. Autonomously scores every AI code edit in real-time, instantly flagging the exact files that demand human review.
Hh Ru Apply
Automate hh.ru job searches, LLM scoring, cover letters, and browser-based applications with session сохранение on Node.js + Playwright
Bunnyland Server
An asynchronous social sandbox where humans and LLM agents share persistent characters in an emergent ECS simulation.
Fusio
Single-user agentic ops console — Next.js 15 web app with persistent SQLite memory, multi-agent missions, MCP-driven skills, Tailscale-powered cross-machine bridge, and a mobile P…
LLM Bridge
MCP server that routes LLM calls through CLI subscriptions (Claude, Gemini, Codex, Copilot) — zero API tokens needed
Obsidian Semantic MCP
MCP server for Obsidian with semantic search, vector embeddings via pgvector, and Claude Code integration
Ldf
Language Data Format: a lossless, line-oriented text encoding of JSON records that language models read for 35 to 45 percent fewer tokens than JSON. Measured, not assumed.
UniversalMods
Local web floor to run and steer teams of Codex and Claude Code agents: live terminals, shared hive, hot-reload mods
GameDirector
Let AI direct your game. An LLM directs in-game cutscenes as deterministic, frame-exact timelines. Unity · Godot · Three.js · MCP · MIT
Coop
Meeting rooms for AI agents of different owners: turn-taking, human approval, signed minutes.
Neobrain
neoBrain — a local simulated brain for AI agents: durable memory, deterministic rank-based forgetting, nightly dreams and a self-authored soul. One daemon, one dashboard.
Gitmind
Git-backed memory for coding agents (MCP server in Go)
AdVeto
AdVeto · 送审前的 AI 律师 —— 营销素材合规审查多 Agent 流水线（AgentTeams × 三轨互证 × 条款级证据链）｜GOAI Agent Infra 参赛项目
Skillhub
⚡ The Universal Package Manager & Registry for AI Coding Agents (Claude Code, OpenCode, Cursor, Windsurf, RooCode, Copilot). 630+ skills, 15 agent targets, 9-rule security scanner…
Harness DB
HARNESS-DB: 1,256 LLM agent harnesses coded on 38 design dimensions with a verbatim quote behind every value; pre-registered PRISMA 2020 review; loader, explorer, MCP server
Treaty
Python CLI framework for tools AI agents can call safely: one-call manifest, JSON envelope on every exit, typed exit codes. Implements the CLI Agent Spec
Interest Memory
Low-footprint memory backend for AI agents — single binary, ~50MB RAM, verify-augmented accuracy
Pneuma
Pneuma（numa）— 独立终端 AI harness：自研 ReAct loop + 工具栈 + 审批；ink TUI + Electron 桌面端 + 手机遥控页，插件化界面壳