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.
Agentguard Firewall Py
Python port of @mukundakatta/agentguard: network egress firewall for AI agents
Councilverse
Open-source AI council formations for multi-agent debate. 15 structured methodologies, three-valued voting, and sprint contracts.
Commitiq
AI-powered CLI that turns your git commits into readable work summaries — across multiple repos, by date range, with MCP server support.
Awesome Claude Tools
A curated list of tools, frameworks, libraries, and resources for building with Claude (Anthropic). Maintained by Claudexia.
Axguard
Adversarial security testing for AI agents — MCP, A2A, x402/L402, and live tool-use. Tests as YAML, evidence as JSON.
Windtunnel
Unittest for tool-using LLM agents: reproducible scenarios scoring outcome, trajectory, constraints, and robustness.
Cubelife Example Claude
Example: Claude API agent with a CubeLife pixel-art character
LLM Cost Optimizer
Cut your LLM bill by 30-70%. Analyze OpenAI/Anthropic/Google/DeepSeek API logs, calculate cost, and get actionable optimization recommendations.
Kew
Local LLM agent orchestration with a persistent worker pool. Run specialist agents (developer, debugger, tester, security, docs) in parallel via CLI or MCP — backed by SQLite, pow…
Review Replay
Verify that every PR review comment was addressed. CLI + GitHub Action for agentic and human review workflows.
Xlore
Git-based cross-chat memory your AI agents maintain — across Claude Code, Cursor, ChatGPT and more
Pi Meter
Cross-session LLM spend tracking, budget alerts, and auto-downshift for AI coding agents (CLI + MCP + Claude/Cursor skill + pi extension).
Dream Skill
Reconcile your Obsidian wiki against Claude Code session signals — flag stale, missing, and contradicted facts for review. Solves the stale-LLM-wiki problem.
Ctxdiet
Detect, fix, and measure AI coding-agent context-token waste across Claude Code, Codex, Cursor, Gemini & Copilot.
SemanticDrift
Research proposal and pilot study on detecting temporal behavioral drift in Model Context Protocol (MCP) tool descriptions.
Agent Learn Skill
LLM & Agent 知识学习、自适应考试和学习路径推荐 Skill 插件 —— 支持 MCP 增强模式与纯本地降级模式
Keepsake
Sovereign, local-first, zero-knowledge long-term memory for LLMs and AI agents — yours like a crypto wallet. Apache-2.0, no telemetry, runs offline.
Agentic Pipelines
Composable, agentic pipelines for MCP — fact-checking (DSPy), RAG (hybrid search), document intelligence (DeepPipe), and clinical voice (Groq/ElevenLabs). 31 AI tools, one command…
Elder Council Harness
A local-first, multi-model council harness for high-stakes decisions — risk-gated escalation, fail-closed consensus, hash-chained audit. Eight councils (six cyber + a general busi…
JobSniper
Intelligence-driven job search decision system.
Nilux
AI coding agent that lives in your terminal
Pharma Intel MCP Demo Lite
A lightweight, reproducible demo of pharma competitive-intelligence graph construction and GraphRAG Q&A: 14 investor-deck PDFs → a Neo4j knowledge graph via neo4j-mcp-workspace-te…
Opencampus AI Framework
Open-source framework for building secure AI-powered administrative workflows using MCP, FastAPI, and agentic orchestration.
Valj
JSON Schema validation toolkit
Laravel AI Assistant
A drop-in agentic AI assistant for any Laravel app: streaming chat, tool calling, human approval, and conversation history.
Agentic Crm Blueprint
Compendio tecnico sobre arquitetura, metricas, governanca e engenharia de agentes de IA integrados a CRM e atendimento conversacional (PT-BR).
Mu SDK Python
Python SDK for Memory Universe — a wire client for agent and application workflows. Apache-2.0.
Multi MCP Agent Router
A multi-agent AI router built with Gemini and MCP, connecting specialized agents to domain-specific tools including a custom GitHub MCP server.
Litellm MCP Gateway
MCP server exposing multi-provider LLM completion via LiteLLM — cross-provider fallback, pre-call budget enforcement, per-request cost attribution.
Imc MCP
MCP server for H3C iMC REST API — let AI assistants query network devices, alarms, performance & topology in natural language. 15 read-only tools, Streamable HTTP, Digest auth, si…
Guarded Server
An MCP server with a real security model and the tests that prove it: three permission tiers with human approval for destructive tools, a path jail, tool results marked as untrust…
Bradar Ponytail
Режим ленивого сеньора для AI-агентов: меньше кода, дешевле и быстрее без потери safety #AI #Агенты #Coding #Skills #MCP
Uhermes
🐱 从100行代码起步，逐步进化的AI Agent - 配合《缸中之脑出缸记》系列
Oas Execute MCP
A safety layer between a language model and a broker order. MCP server: seven tools over a swappable broker backend, with the failure modes tested rather than assumed.
Weather MCP RAG Assistant
MCP-based AI weather assistant using OpenWeather API, RAG, ChromaDB, LangChain, and Groq LLM.
Worker Starter
A minimal, dependency-free MCP (Model Context Protocol) server for Cloudflare Workers. One file, plain POST, and the three silent traps that cost me a production outage.
Moonclaude
A terminal AI coding agent in MoonBit: a behavior port of OpenClaude. Streams from Anthropic or any OpenAI-compatible endpoint, runs tools under a rule-based permission gate, spea…
A2a MCP Multi Agent Framework
Production-ready Agent-to-Agent (A2A) communication framework with Memory Context Protocol (MCP) — demonstrating scalable, decoupled multi-agent AI architecture with async messagi…
Flyrank Capstone Social Studio
AI-powered multi-platform social campaign publishing platform built for the FlyRank Backend AI Engineering Internship Capstone.
Deploying Agentic AI Apps Workshop
Workshop Repo: Deploying Agentic AI Applications
Cursor Amnesia Kit
Stop your Cursor AI from forgetting, mixing up concurrent chats, and redoing finished work. Zero-dependency rules + tools: content-fingerprint session recall + reconcile-first git…
Tellmphone
Let your LLMs call each other — a local MCP switchboard for coding agents
AI Edu
Manufacturing AI, on-prem LLM, RAG, and agent systems - bilingual (EN/KO) education from factory-floor experience
FO Claude Automation
Production LLM agent workflows for 392K-follower brand ecosystem — Claude API + MCP Architecture
Usesend MCP
FastMCP 3 MCP server for the useSend email platform — 33 curated tools (emails, contacts, campaigns, domains, analytics) over stdio.
Drawio MCP Http
HTTP proxy for the draw.io MCP server with temporary shortened diagram links
Keel Sec Guard
Automated AI security auditor and SAST scanner powered by Google Gemini. Runs locally via CLI/Agent Skill and in CI/CD via GitHub Actions.
Sqlgate
A deterministic, fail-closed write gate for LLM-generated SQL, exposed over MCP. The model can't talk its way past it.
Tollgate
Safety layer for AI agents — Protect · Route · Prove. Budgets, tool-loop hard stops, failover, chaos DR proof. OpenAI drop-in · MCP · n8n.
Tokenzip
Vision models pay for tiles, not megapixels. Per-provider token math, exact + budget resize, zero-dep PNG/JPEG codecs, Claude Code hook, MCP server.