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.
TalentFabric AI
Five-agent certification readiness platform built on Microsoft Agent Framework, all three IQ layers (Foundry/Fabric/Work), and Microsoft Learn MCP — Agents League Hackathon.
Xiigen General Skills
Open-source AI agent skills for safer Claude, Codex and Cursor coding workflows
Agent Smithers
Agentic AI assistant for Matrix with multi-provider LLMs (OpenAI, xAI, LM Studio), tools, MCP, and image/video generation
Kiara
Kiara - KI Assistent für Retrieval und Analyse
Tokenscache
AI token waste elimination and intelligent cache layer for multi-provider agents
RepoMem
Persistent memory for AI coding agents — SQLite + FTS5, zero dependencies, zero API keys
Lich
Ruthless, algorithm-backed code review. Tests AI-generated code in an isolated sandbox to mathematically prove it works before merging.
Simosphere MCP Examples
MCP integration examples for SIMOSphere AI — connect CRM, ERP, documents with AI agents. GDPR-compliant.
Scrape Website MCP
MCP Server for Incredibly High Performant web scraper (seconds for what takes others lots of minutes) - battle tested on millions of websites.
Agent Code Buddy
Companion approval surface for local coding agents
Mcpquick
LLM toolset evaluation platform
Oac
Open Agent Capsule — file-first portable agent state (identity, memory, procedures, skills) across Claude Code, Codex, Gemini CLI, OpenClaw, OpenCode, and MCP
Cachly Intellij
Cachly Brain — IntelliJ IDEA plugin for AI memory monitoring. Status bar widget, lesson viewer, storage usage.
Statepilot
Predictable browser runtime for AI agents with memory, validation, recovery, and MCP integration.
Compliance Watch
Contract and invoice compliance auditor built with Claude API. Hybrid RAG, tool use, MCP server, prompt evaluation, extended thinking. Full pipeline — not a chatbot.
Regulations MCP
MCP server for live U.S. federal regulations — Federal Register, eCFR, Regulations.gov. Works with any LLM (Claude, GPT-4o, Gemini, Mistral, Llama, Ollama).
Agntz
Portable YAML agents for TypeScript and Python, with embedded execution, hosted APIs, evals, traces, and durable memory.
Yeti Agent
Yeti Agent — Autonomous AI Agent Platform. 24/7 browser automation powered by LLMs + CDP. Built in Nepal 🇳🇵🏔️
Dust Tt
Dust — independent third-party profile of a public API surface, by API Evangelist. Dust is a Paris-based enterprise AI platform for building, deploying, and operating teams of AI…
Rag Pgvector Demo
Production RAG pipeline: pgvector + nomic-embed-text + Claude API with MMR reranking and eval harness
AmberClaw
Lightweight personal AI assistant framework — any LLM, any chat platform, 4k lines of Python
Vibe Coding Prompts
30+ structured prompts for building real apps with AI. Landing pages, dashboards, APIs, CLIs — production-quality code on the first attempt.
Caduceus
Provider-agnostic transport and routing for LLMs: normalize OpenAI, Anthropic, and Gemini, route by cost, quality, or latency with per-model circuit breakers, USD budgets, automat…
AI Agent Tool Augmentation
Multi-agent LLM system that augments AI agent tools using code generators (ReAct-based code generation, security review, Docker sandbox execution)
Switchyard
Detect when Claude silently falls back from Fable 5 to Opus 4.8, log it to a local tamper-evident ledger, and keep your work on the frontier model.
AI Rag Platform
Plataforma de IA com RAG (retrieval-augmented generation) em Python + FastAPI, vector database, embeddings, LangChain e servidor MCP (Model Context Protocol).
Harness Engineering Lab
Evidence-first, local-first Windows Agent Harness with persistent conversations, controlled tools, verification, and plugins.
Easymem
An LLM wiki your coding agent writes — agent memory you can open and read. easymem stores it, searches it, and links it. Plain markdown on disk, no vector database. Runs with npx…
Session Migrator
A cross-agent session memory migration layer: migrate or compress a conversation based on the target model's context window. MCP server + Python library.
Ros2 Agent Workflow
Safe Agent-to-ROS2 MCP framework: FastMCP, fail-closed SafetyGateway, Gazebo TurtleBot3 Burger case, 505 tests, verifiable evidence
Page Agent SDK
给网页一个会改页面的 AI 助手。一行代码挂载对话框，AI 通过工具按 schema 安全读写页面数据，实现「对话式」搭建/编辑/运维。
Tomilite
AI-powered personal productivity desktop app — chat with an AI agent that manages tasks, notes, emails, and daily reports. Local-first, MIT licensed.
Ownware
The open, model-agnostic platform to build your own AI agent and run it everywhere — self-hosted, safe by default.
Loopr
A live dashboard for loop engineering to monitor every step of your loops. A maker builds, a checker grades it against your rubric, and it repeats until every criterion clears you…
Social Dive
Social Dive 🤿 — Agentic internet-access layer. Read and search 16+ internet sources (arXiv, GitHub, YouTube, etc.) with high-speed Rust HTML parsing and LLM summarization via NVID…
CreateYouAI
Modular AI Skill repository. Build your own AI like stacking LEGO blocks. 模块化 AI Skill 仓库，像搭积木一样构建你自己的 AI。
Libero
The open-source AI teammate for Slack. Self-hosted, credential-isolated, every tool call audited.
Gemini4codex MCP
Model Context Protocol (MCP) server bringing Gemini's advanced agentic capabilities to Codex and local IDE workflows.
Aurum Recall
Sovereign, human-readable AI memory — a store + MCP server + a visual context-routing lattice (ContextQR). Route before you retrieve.
Cordis
Helping AI agents remember what happened, learn from evidence, and approach the next task differently.
Codedistill
CodeDistill Community Edition — open-core (AGPL-3.0). The full scratchpad→classify→verify→provenance loop; commercial editions add MCP write tools, code anchors, and more.
JaySoft AI Tools
Codebase intelligence shell and SDK — pip install jsat
Origin Memorycore
LLM Agent 记忆治理层 —— 热层/冷层双层,自动溢流 + 自适应召回阈值 | Memory governance layer for LLM agents — hot/cold tiers, automatic overflow + adaptive recall threshold
Tech Radar Agent
Local AI-agent research copilot: hybrid retrieval (E5 + BM25 + RRF + cross-encoder), bounded ReAct agent with deterministic citation validation, FastAPI + React chat UI, and a rea…
Alfa
A coding agent that lives in your terminal. Local-first, your own API key, no telemetry.
Deep Dive Capstone
Codebase Q&A with (path:line) citations — the capstone of a from-scratch AI-engineering series. Built in 8 eval-gated stages (chat → RAG → agents → hardening → production), provid…
Healix
Healix is a full-stack AI healthcare assistant featuring real-time token streaming, multi-format medical document parsing (PDF, Word, Lab reports), live clinical web search, visio…
Mire
Test-pattern generator for model endpoints: a known signal in, a look at what comes out
YourBrain
Local-first AI memory engine in Rust. Remembers across sessions, auto-resolves conflicting facts, validates answers against a knowledge base, and caches grounded responses. Single…
Aiox Opencode Adapter
AIOX OpenCode Adapter: 13 agentes de IA especializados para OpenCode. Orquestração multi-agente com @dev, @qa, @architect, @cybersec e mais. Suporte a MCPs, presets, documentação…