Best LLM AI Skills & MCP Servers

Model Context Protocol (MCP) server for fal.ai - interact with AI models through Claude and other MCP clients. Now with Platform API v1 support!

Playwright-based same-origin documentation crawler for docs-to-mcp

MCP server: persistent memory, compaction, semantic recall (Node.js port)

FDKEY verification middleware for MCP servers — gate AI-agent access behind LLM-only puzzles. Runs on Node 18+, Cloudflare Workers, Bun, and Deno.

Shared TypeScript interfaces for the docs-to-mcp pipeline

A Bugsnag MCP server for interacting with Bugsnag API

HTML cleanup and Markdown conversion for documentation pages

MCP (Model Context Protocol) plugin for majk-chat

Simple MCP server for Claude Code one-shot execution

Code Intelligence MCP Server - Smart context for your LLM coding agent

Core evaluation engine for MCPLab — agent adapters, MCP client, scenario runner, and result types

MCPLab - Test and evaluate MCP servers with LLMs — run evals, compare agents and launch the MCPLab web app

Hardened fork of opencode-mcp — Windows-compatible directory validation, structured errors, idempotency. Drop-in replacement for the upstream package.

Generic chatbox engine, UI components, and helpers. Self-contained build — consumers only need react + styled-components.

MCP server that exposes MCPLab evaluation tools — query runs, results, and traces via the Model Context Protocol

MCP-first SKILL.md routing for AI agents: local embeddings, SQLite sessions and telemetry, optional LLM rerank paths, regex route policies and project overlays, companion conversation preset, parity CLI.

Local-first MCP daemon scaffold for the LLM Wiki system.

LLM provider tool format adapter for MCP — supports OpenAI, Claude, Bedrock, Gemini, and Mistral

포트원 사용자를 위한 MCP (Model Context Protocol) 서버입니다. 포트원 개발자센터, 헬프센터 등 공식 문서 내용을 LLM(Large Language Model)에 제공해 정확한 정보를 바탕으로 사용자의 연동 및 질의를 돕도록 합니다.

Convert OpenAPI specifications to MCP (Model Context Protocol) servers with optional Emcy telemetry

Local and OpenAI embedding providers for documentation search — runs 100% offline by default

Token-efficient source code navigation MCP server for AI agents

ChromaDB vector store adapter for semantic documentation search

Interactive CLI for Undisk MCP — undo-first versioned file storage for AI agents