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.
Steam MCP Suite
Steam + itch.io MCP server: store search, prices, reviews+NLP, news, jams (TypeScript)
AI Agent Playground
A hands-on curriculum for learning AI Agent Engineering from first principles
PruferMCP
A Visual Studio 2026 extension that turns your IDE into an MCP (Model Context Protocol) client — connect to stdio or HTTP/SSE MCP servers, discover tools, fill their parameters, a…
Effect Browser
Effect Browser runs one-query research and browser tasks through durable, action-bound approval and crash-recovery controls that avoid blind retries after ambiguous external effec…
Cartografo
Draw, execute and evolve a work graph per problem class. You declare the problem; the system draws the map.
Memware
Memory for AI agents that only remembers the latest truth: a bi-temporal belief ledger + transcript index in one SQLite file.
Trust Check
Runs the full MCP trust & safety trilogy — mcp-doctor + mcp-fuzz + mcp-reality-check — as one GitHub Action for CI, or one Python package (GuardedSession) for a live agent session…
Steadbot
Self-hosted team of AI agents you message like colleagues: async delegation, a shared browser and desktop, long-term memory, a skill pool, and bots in Feishu/Slack/Telegram. TypeS…
AI Engineering Cookbook
Reusable production AI patterns: RAG with pgvector, MCP server boilerplate, voice agent skeleton, eval harness.
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.
Openclaw Atlas Showcase
A multi-agent AI operations system: 15 specialized agents + ~80 automation scripts running real marketing, SEO, and CRM ops. Built on OpenClaw + MCP.
Token Save MCP
Stop your coding agent burning context on file reads. Delegates big reads to a cheap worker model and returns only the answer — 87-99% saved, measured per call. A hook enforces it…
Era
Build, test and benchmark agents across a complete simulated enterprise
Algocode
Algorithmic Code & Backlog Analysis Engine with NL-DSL-LLM Architecture and MCP Server
Painpoints
Find the architectural pain points in any codebase. Scores every file on layering, complexity, data access, failure handling, UI cost and trust-boundary risk against Google, Amazo…
Hoheit
Vendor-neutral AI orchestration endpoint - OpenAI-compatible, with explainable routing across cloud and local models, YAML agents and MCP tools. Self-hosted.
Medical AI Assistant V0.2
AI ENGINEER PROJECTS
OpenRomeo
OpenRomeo — AI coworker on your desktop that delivers finished work: latest frontier models (GPT-5.6, Claude 5, Gemini 3.6, Kimi K3), docx/pptx/pdf skills, image generation. Fork…
Promise Ledger
Evidence-backed ledger for post-sale commitments with human approval, explicit supersession, accepted fulfillment evidence, and a hash-chained audit trail.
DeepSupport OS
DeepSupport OS — Enterprise IT Help Desk Agent Harness：M365 Help Desk · Skills/Subagents · HITL · 文件工作区 · 自动化评测。Vue3 + FastAPI + Deep Agents + LangGraph + RAGLab。
Quant Trade Agent Tools
Provider-neutral intelligence plane with REST, MCP, CLI, pi and experimental dsh adapters for quantitative trading analysis.
Campuspilot
AI-powered multi-agent coach for Indian campus placement prep — Resume, DSA, GD/HR, Aptitude
Aiprice
大模型 API 比价数据（42 模型 x 14 厂商），公开 JSON API + MCP，Agent 可读 llms.txt
Ollamancer
Fully-local terminal AI agent for Ollama. 34 tools, MCP, local RAG, deterministic hallucination checks. No cloud, no API keys, nothing leaves your machine.
Spendiq Prototype
Conversational AI copilot over procurement, AP, and contract data — grounded answers with citations to specific rows and clauses. Built for the TechTorch AI & Data Engineer challe…
Jobo
Evidence-grounded job application copilot with Discord, GitHub, public ATS, and Tsenta MCP support
Sap Intelliops
Agentic AI system for enterprise incident resolution using LLM agents, RAG, tool calling, MCP, and governed execution.
Technocore Chat
HTTP-native chat and notes for agents whose sandbox only allows webfetch — every write is a plain GET. Runs technocore.chat.
AI Based Data Engineering
Companion code for AI-Based Data Engineering (Packt) by Richie Bachala: runnable examples, the OpsPulse dataset generator, and per-chapter code for building the data platform AI a…
ConvergeLoop
通用型 AI 对抗性验证引擎 - 11 角色 +47 扫描器 - 修到真完美
Riah Todo
Today's list as a note by the Windows clock, or as a page on a Mac. One local JSON file. No account, no cloud.
Workbuddy Agent Card
A2A Agent Card endpoint for WorkBuddy Skills Agent (A2A protocol 0.2)
Cid
L.ai · Gate (CID) — per-token validation for LLMs. Catches hallucinations, math errors, and fallacies in real time. 5+ gates, 1,606 facts, 630KB WASM.
Managed Agent
从零实现的 Agent Runtime：不依赖任何框架，基于 LLM 原生 API 复刻 Claude Code 核心工程机制。七课渐进式教程，每课含代码/测试/文档/简历/面试题。
Content Ops
MCP server for CMS content operations with deny-by-default write scoping and audit output
AI Engineer Frontier
🔭 AI Engineer Track 3 of 4 — open-weight frontier models, Hermes and the Nous stack, post-training, GRPO, inference engineering, MCP. ~88 hours, 9 phases.
Sayhi
识海 Noetide — 本地优先、零依赖的个人记忆系统：AI 只提候选不写入，每条记忆带证据链。Local-first personal memory system, pure Python stdlib + SQLite, web UI + MCP.
AI Code Review Agent System
A production-ready, multi-agent code review system that leverages LangGraph and LLMs to automatically analyze code for bugs, security vulnerabilities, performance issues, and code…
Argus AI Reliability Platform
Self-healing AI reliability platform: LangGraph multi-agents + MCP tool execution + RAG-grounded Gemini evidence to detect, diagnose, and safely recover from LLM/RAG/agent failure…
Deadwax
An agentic music librarian with a deterministic validator, a repair loop, and a measured eval suite. LLM tool use, RAG, tracing and MCP.
Trusted Transcription
Catches an AI's confident mistakes before they reach a client — what turns an impressive demo into something you can invoice.
User Research Workspace
证据驱动的 AI 用户研究与智能体平台，支持网页研究、Persona、访谈与可追溯报告；Evidence-driven AI user research and agent platform with durable workflows, evidence-grounded reports, and governed tool execution.
Nivara AI
The AI support layer for Nivara Desk: answers what it can safely answer, asks when a request is ambiguous, and escalates the rest to a human. Python, FastAPI and Qdrant, with hybr…
Work Intelligence MCP
Local-first assistant that watches your Jira/Slack/GitHub and learns which tools actually solve which problems — an agentic loop graded mechanically, no LLM-as-judge.
Chatbot Client
AI-powered MCP chatbot built with Gemini, LangChain, FastMCP, Streamlit, SQLite, Manim, and Docker. Connects multiple MCP servers for intelligent tool calling, expense management,…
Real Time YouTube Script Generator MCP Server
made a agent that finds the trending things and create script to generate video
Investigation Agent Client
AI investigation agent for risk analysis with LLM planning, tool calling, MCP capability reuse,policy grounding, structured artifacts, and evaluation.
Qwen Eventflow AI
AI-powered assistant "EventFlow_AI" for Solace Event Portal and Event Broker, enabling Admins and End Users to discover and manage event-driven architectures through natural langu…
Newsletter MCP
MCP server: newsletter-mcp
Seo Content MCP
MCP server: seo-content-mcp