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.
Sapphire Agent
A personal AI assistant agent that works on file-based, local-first sapphire-framework workspaces together with you
Clayworks Lite
The Claude Code operator scaffolding I built without writing the code. Open-sourced under MIT for anyone else doing the same.
AI Agent Deep Dive
Explore AI agent architecture with deep dives, PDF notes, and a minimal Python teaching project for learning core agent structure
Eos
The GitHub Org Context API — the context layer for AI across your entire GitHub organisation. TypeScript SDK, official MCP server, and CLI.
Alyce Agent
Experimental byproduct of learning agent
Intelligent Knowledge Assistant
Unified conversational AI that routes plain-English queries to hybrid RAG document search or live Jira — built with LangGraph, FAISS, BM25, MCP, and RAGAS.
Langchain From Zero
🚀 从零到精通 LangChain - 21章完整中文教程 | 使用 vLLM+Qwen、Langfuse、Playwright | Agent/RAG/LangGraph/MCP 全覆盖 | 100+示例
Hands On Rag
Comprehensive guide and repository for building, understanding, and implementing Retrieval-Augmented Generation (RAG) systems with Python.
XidaoApi
OpenAI-compatible AI API gateway — 100+ models, smart routing, failover. Claude, GPT, Gemini, DeepSeek, Qwen, Mistral. Free $10 credit.
Claude Agent Ledger
Per-subagent cost attribution for Claude Code. Reads local JSONL session logs, computes shadow cost at marginal Anthropic API rates with proper TTL pricing.
Youtube Transcript CLI
Fetch YouTube transcripts/subtitles from the CLI or Node — free, no API key, works in 2026 (handles PoToken).
Inaria
Condensed Lighthouse audits as small JSON — built for piping into AI tools.
Loop Agent
Autonomous software delivery from product brief to verified implementation. Loop plans, builds, tests, and repairs in a task workspace, then hands back reviewable artifacts or Git…
Harper Mcps
MCP servers for Claude Code: Obsidian vault, SSH+nmap, Windows WinRM, and OSINT research
RudrenduPaul
GitHub profile README
Cronos
Black Box Recorder for AI Agents —MCP
Zero Context Protocol
Documentation, architecture, benchmarks, and protocol design for ZCP, a runtime-first protocol compatible with MCP.
Tcc AWS Agent Platform
Configuration-driven, provider-agnostic runtime for declaring AI agents in YAML and deploying them on AWS — built on the Strands Agents SDK and Amazon Bedrock AgentCore.
SuperbrainSdk
Distributed RAM-speed FAISS for AI agents"
Llama Index Tools Ejentum
LlamaIndex tool spec for the Ejentum Reasoning Harness. Wraps the hosted Ejentum MCP server and exposes 8 tools (4 harnesses × dynamic + adaptive).
Nvidia Glm Proxy
Proxy for NVIDIA NIM API that fixes GLM-5.1 tool_call streaming bugs (numeric IDs, missing function.name, ID instability). Zero dependencies.
Xidao Cookbook
Migration guides, rollout checklists, cost-control patterns, and LLM routing recipes for OpenAI-compatible APIs. Covers OpenRouter alternatives, failover strategies, and productio…
Maix Agent
A hybrid AI-Agent implementation with persistent memory, programmable architecture, and multi-model routing.
Samia
SAM/IA — biologically-inspired persistent memory for AI agents: tiered decay, dual-process recall (episodic chainograms + semantic atoms), restorable supersession, REM-cycle conso…
Schemafit
Provider-aware structured-output / JSON-Schema CI linter: fail CI before your schema 400s on OpenAI, Anthropic, or Gemini.
Oncall Copilot
Provider-agnostic AI on-call assistant — RAG + a tool-using agent + an MCP server + an eval harness — runs on Claude, OpenAI or OpenRouter. A hands-on learning project.
Viko Agent
Self-hosted multi-project AI developer agent powered by Hermes + WhatsApp
Domesticoracle
Self-hosted AI home assistant with a built-in governance layer — policy engine, approval queue, and Ed25519-signed audit ledger. Privacy-first, open source. LangGraph + Claude Son…
Memoturn
Open-source AI engineering platform — LLM observability, evals, metrics, prompt management, playground, and datasets. OpenTelemetry-native, self-hostable. Because "it worked when…
SpecImpact
設計書をHost LLMとEvidence Graphで構造化し、自然文の変更から影響範囲を検証・管理するローカルファーストOSS
Cachly Go
Official Go SDK for cachly — persistent AI memory and managed Valkey/Redis with semantic caching. Free tier, EU-hosted.
Cachly Java
Official Java SDK for cachly — persistent AI memory and managed Valkey/Redis with semantic caching. Free tier, EU-hosted.
Lab.abvx
Public catalog and control plane for the ABVX AI coding tools stack: repo context, orchestration, skills, discovery, and proof surfaces.
Aikit Runtime
Agent-native, governed AI runtime for Rust, Python, and TypeScript — native providers, MCP, tools, routing, memory, budgets, audit, and containment.
Feedspace Cookbook
Open AI skills for customer reviews: analyze by lens, build case studies, spot trends. Agent Skills standard - works in Claude, Cursor, Codex, Gemini CLI, or any MCP client.
Duin Governed Agent Memory
Agents that earn your trust. A harness that keeps an agent's long-term memory, model of your world and permissions as Markdown you own, governed at every step: facts labelled by w…
AI Community
Open AI community by Data Science Research Perú. Learn, build and share projects in AI, Agents, RAG, MCP and AI Engineering.
Pi Mem
Harness-verified memory recall for coding agents — re-checks a memory note against ground truth on read (verified/stale/unverifiable). Built on the pi-gate trust boundary.
Swarmbreaker
Load and chaos testing for AI agent orchestration plumbing: adversarial mock model endpoint + mock MCP tool fabric, knee detection with CIs, honest confidence labels.
Agentic CAD Skills
The tool layer for CAD agents: skill definitions, MCP interfaces, typed tools and post-condition checks. Part of the Agentic Mechanical Engineering collection by WOGO.
Psychelink
?? PsycheLink - Mental-Health AI Companion: Intent Classification + Milvus RAG + SSE Streaming + Risk-Alert Closed Loop. Built with Spring Boot 3 / Spring AI.
M8m
AI memory observability, provenance & security
Awesome Ag Ui
AG-UI protocol: 340+ agent integrations, SDKs, middleware, and apps, with a capability matrix per framework.
Karmx Agent
Terminal coding agent with prompt enhancement, a context engine, live browser preview, local fusion, and any OpenAI-compatible model.
Context Bank
Context infrastructure for LLMs — portable memory, model switching, skills & governance. Switch GPT ↔ Claude ↔ Gemini; your context stays. npm: @losi-ai/*
Plc AI Agent
Local AI agent (Ollama + MCP) for PLC diagnostics & SCL code generation via OPC UA and TIA Portal Openness — 100% local, no cloud, no API keys.
Libre Box
Self-hosted LibreChat + MCP stack that gives AI agents a real, persistent Linux computer — shell, TTY sessions, background jobs and files in a hardened Ubuntu sandbox.
Hisho Kun
Remote Approval Companion & Desktop Pet for AI Coding Agents (Claude Code, Cline, Cursor)
Agent Engineering Roadmap
从会调 LLM API 到能把 Agent 送上线：按依赖关系排的六阶段学习路线（中英双语）· An opinionated roadmap for becoming an AI agent engineer
Pi Workbench
Pi Desktop — a desktop workbench for coding agents: Pi, Claude Code and Codex in one app. 桌面版编程 Agent 工作台。