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.
Signal Prospector
A signal-based B2B prospecting engine on free infra: 8 buying-signal detectors, an explainable ICP scorer, free MX-validated email enrichment and AI outreach - via CLI, Flask and…
AskSQL
AI database chat for Node and the browser: ask in plain language, review the query, get answers. Postgres, MySQL, SQLite, DuckDB, Oracle, MongoDB. Read-only AST guard, React UI, M…
Visual Scene Ontology
An image is not a sentence: a VLM's description of one is unvalidated prose. VSON makes every claim about an image — object, property, spatial relation, action — a graph assertion…
Reposnap MCP
Free MCP server to ingest any public GitHub repository directly into your AI context. Works with Claude, Cursor, Windsurf, and any MCP client.
Tool Schema
Convert any JSON Schema into a valid tool / function calling schema for OpenAI, Anthropic, Gemini and MCP. Zero dependencies.
Geistr Core
Reusable desktop-first AI app foundation built with Electron, React, and the Pi SDK.
Trimcp
MCP proxy to reduce LLM token costs, built in Rust
Agentic Gen AI Frameworks MCP VectorDB
A comprehensive collection of modern Agentic AI and Generative AI frameworks used to build autonomous, multi-agent, and production-ready AI systems. Covers LangChain, LangGraph, C…
YakAgent
Lightweight Python agent framework — tool-calling loop, permissions, sub-agents, streaming. 17 LLM providers, 15 built-in tools.
Opencode Homelab
Local-first AI coding agent stack: OpenCode + llama.cpp + Qwen3.6 with smart context routing
Humanizer MCP
Public, read-only MCP server: psycholinguistic rules and a deterministic checker for making written prose read as human, not machine-generated.
Goo
GOO — terminal-first agentic AI coding assistant built with Go: MCP integration, parallel sub-agents, 3-tier safety gating, persistent memory, task management.
Prpeek MCP
MCP server that returns GitHub PR feedback — review comments, resolved status, review summaries — in one normalized, token-efficient JSON call
Vla
A CLI-based agentic coding harness with persistent memory and LSP-backed code intelligence.
Claude Forge
Zero-dependency multi-agent build, automation and review system for Claude Code. 18 agents, 23 skills, a live per-project dashboard, and a /setup-forge onboarding wizard. One comm…
Runninghub MCP
给任何 MCP 客户端装上 350+ 多模态模型：npx -y runninghub-mcp@latest 一条命令接入图像/视频/音频/3D 生成 + ComfyUI 工作流 + AI 应用 + LLM 对话。零构建，--scope 裁剪。适配 WorkBuddy/Claude Desktop/Cursor/OpenClaw。开发者 AI芳程式，反馈 z…
Tokcodecut
Token-optimized MCP server giving Claude surgical read access to source files — structure, skeletons, symbols, imports, cross-file refs. Cuts 70–95% tokens on code nav.
AdoptViaAI
Claude API CLI demonstrating all 5 CCA-F certification domains — chat, tool use, agents, MCP, and safety guardrails in a single production-pattern tool.
Aiwatcher MCP
AI news ingestion, distillation, and alert system
AI Knowledge Hub
The world's best open-source AI & LLM engineering resources curated, annotated, and organized. Covers RAG, agents, fine-tuning, prompt engineering, vector databases, transformers,…
Swagger CLI
Generate runnable MCP (Model Context Protocol) servers from Swagger/OpenAPI specifications. Supports OpenAPI 3.x and Swagger 2.0, auth configuration, path filtering, and multiple…
Chunktuner
Benchmark chunking strategies for your RAG corpus. Get a recommended config. CLI, Python library, and MCP server.
Knowledgeforge
Enterprise-ready AI Knowledge Agent enabling secure, multi-tenant natural language search over internal documents. Delivering accurate, cited answers governed by strict role-based…
Tokenitdown
Turn any document or web page into clean, LLM-ready Markdown, with visible quality control, RAG-ready output, real token economics, and native AI-agent access over MCP. Self-hosta…
AI Dial Memory Backend
Persistent memory service for AI agents running on the DIAL platform, gives agents long-term memory across conversations by exposing MCP tools for storing and retrieving data.
Skillens
🔍 Is this worth learning? A CLI that evaluates learning resources (courses, videos, papers, repos) from market demand down to info density — in 3 seconds.
Wikimcp
Git-backed multi-user wiki MCP server — long-term memory for any AI. Inspired by Karpathy's LLM Wiki pattern.
Awesome Agentic Web
A curated list of awesome resources for the agentic web - the protocols, SDKs, and specs that let AI agents discover, understand, and act on websites (MCP, ACP, AP2, A2A, llms.txt…
Fabrico Collections
Opinionated Claude Code collection — commands, subagents & skills for autonomous software delivery and legacy app modernization.
Datadoe MCP Claude Code
This repository is a starter template for integrating DataDoe MCP with Claude Code CLI in a secure, team-friendly way.
Claude Init
Production-grade Claude Code harness — a spec-driven, TDD-first, verification-gated, security-aware .claude/ scaffold you drop into any repo with one command.
AI Orchestrator
Multi-provider AI router with cost tracking, RAG memory and live dashboard. Routes tasks across Claude, OpenAI, DeepSeek and Gemini via CLI and MCP server.
Aqueduct Data Agent
Aqueduct — 工业级数据开发 Data Agent：需求文档 → 15 个标准交付物（DDL / ETL SQL / DQC / 血缘 / 设计文档）
CHAOS
Run models that do not fit in your RAM. Keeps the always-read weights resident, streams the routed experts from disk.
Skillassay
Static analyzer for AI coding-agent context — and an Agent Skill your agent can run. Measures always-on context cost of CLAUDE.md, AGENTS.md and Agent Skills; finds skills that wo…
ERP AI Agent
Open-source enterprise AI agent: LLM tool-calling engine, permissions, RAG and a Python analytics engine, with a working ERPNext connector. Architecture guide: noviz.in/how-to-bui…
Cognitive Memory
Cognitive memory substrate for AI agents that encodes selectively, consolidates autonomously, and shares context across sessions.
Gnome Shell Extension AI Assistant
Artificial intelligence LLM chat integration and MCP server exposing the shell environment
Opencode MCP Activate
OpenCode plugin that lets the model start and stop configured MCP servers at runtime
Sag MCP Server
sag-mcp-server
kinti/a11y-toolkit
live announcement monitor. Multilanguage es/en, zero dependencies.
serhiizghama/viber-mcp
mcp`.
Wacli MCP
MCP server for WhatsApp via wacli — search messages, list chats, send texts from any AI assistant
Sensei
Self-hosted AI workspace that compresses prompts before they leave your machine — 79% fewer tokens, measured. Drop-in gateway for Claude Code, Cursor, Aider and any OpenAI/Anthrop…
VFB3 MCP
Explore Virtual Fly Brain data directly through your favourite LLM with the new VFB Model Context Protocol (MCP) tool
Librarian CLI
📚 Any ebook → clean token-counted Markdown chapters. Let Claude read your bookshelf over MCP — and catch it misquoting your books. Deterministic RAG: no embeddings, no network, no…
Sosa
SOSA™ — Supervised Orchestrated Secured Agents. A governance framework for production-grade autonomous AI operations.
Agent Fleet
Multi-agent orchestration for Claude Code CLI. Run specialized AI agents in parallel — research, critique, analyze, fix, and discuss.
Agentenna
Agentenna is the awareness layer for AI agents — a live, token-bounded view of what's happening, rendered straight into context.
AI Runtime Platform
AI Infrastructure OS execution plane: OpenAI-compatible gateway, MCP tool governance, intent proxy, vLLM/KServe/KEDA, OIDC, Redis and telemetry.