Best LLM AI Skills & MCP Servers
474 curated LLM skills and MCP servers — install any of them into Claude, Cursor, ChatGPT, n8n, or any AI stack with one command.
Brick Multiread
Batch file reading — multiple files in one call, deduplication.
Expo Local Docs
MCP server for Expo documentation - reads local .mdx files for blazing fast performance. Works out of the box with zero configuration.
Aeg Intent Gate
A tiny TypeScript approval gate for AI tool calls, MCP tools, and human-in-the-loop workflows.
Web Docs
MCP server for crawling and indexing web documentation - works with any website
Skill Manager
CLI tool that installs and manages AI agent skills, MCP tool routing, and workflow configurations.
Crawlforge
CrawlForge MCP Server - Professional Model Context Protocol server with 23 web scraping, crawling, and content processing tools. Defaults to local Ollama for LLM extraction (no API key needed); OpenAI/Anthropic available as opt-in. v4.0 adds Markdown-firs
Gemini
Professional Model Context Protocol server for Google Gemini AI models with enterprise-grade features
Brick Validate
Validate data — JSON syntax, JSON Schema compliance, TypeScript type checking, lint rules.
Sdk
TypeScript client SDK for Undisk MCP — undo-first versioned file storage for AI agents
Mcp
Model Context Protocol server for Helicone observability platform
Server
MCP server for SharedMemory — persistent AI memory for any tool
Archipel Platform
Reusable MCP (Model Context Protocol) server module for NestJS applications
Veil
A TypeScript library for selective context access, visibility control & safety enforcement for LLMs
Matryoshka Rlm
Recursive Language Model - Process documents larger than LLM context windows
Mcp
VibeCheck MCP — the code intelligence layer for AI-built software, wired into your agent. Truth-grounded, runtime-aware, multi-agent. 16+ verification engines, runtime probes, and live truthpack context for Cursor, Claude, Windsurf, and any MCP-compatible
Mcp
BlockRun MCP Server - Give your AI agent web search, deep research, prediction markets, crypto data, X/Twitter intelligence. Paid via x402 micropayments.
Docs To Chunker
Heading-aware Markdown chunking for documentation embeddings
Seracade
Seracade is a drop-in OpenAI-compatible routing proxy for AI agent teams. Six named capabilities: Call (every request, addressable and replayable), Step (sub-Call routing context inside agent trajectories), Quality Score (calibrated, version-stamped quali
Helius
Official Helius MCP Server - Complete Solana blockchain data access for AI assistants
Codeops
MCP (Model Context Protocol) server providing AI coding agents with universal, language-agnostic development rules. Includes coding standards, testing workflows, git conventions, plan creation/execution protocols, and intelligent project analysis for auto
Els
MCP-сервер поверх INSO Error Logs Service. Read-only tools (search, analytics, fingerprinting, correlations) для подключения Claude Desktop/Code и ChatGPT к логам ошибок. Streamable HTTP transport + stdio для npx-запуска.
Node Red
Model Context Protocol (MCP) server for interacting with Node-RED
Opencode
MCP server that wraps the OpenCode AI headless server API — 80 tools, 10 resources, 6 prompts with multi-project support for any MCP client
Testrail
Model Context Protocol (MCP) server for TestRail integration, enabling LLMs to fetch test cases and metadata.
About LLM skills on iClaude
iClaude is the universal install layer for AI skills. Every LLM skill on this page can be installed into Claude Code, Claude Desktop, Cursor, ChatGPT, n8n, Codex, and more — using a single copy-paste command. No config drift, no per-stack adapters, no manual MCP wiring.