Best LLM AI Skills & MCP Servers

MCP Server for Shopify API, enabling interaction with store data through GraphQL API

Search, create, and retrieve tasks, add comments, and track time through natural language commands.

Structured reasoning chains — think step by step, branch alternatives, revise conclusions, summarize.

Shared state for multi-agent — share context, files, results between agents, broadcast messages.

Multiplexer for MCP tool calls — parallel execution, batching, caching, and pipelining for any MCP server

YouTube MCP server for token-optimized, structured data using the YouTube Data API v3.

Token-efficient, markdown-first Notion MCP server — agents write markdown, never touch raw Notion JSON

A TypeScript framework for building AI agents using the Vercel AI SDK v6

MCP server for Gemini 3.1 Flash with vision, chat, and image generation capabilities

Conformance test runner for FocusMCP bricks — validates manifests, tool schemas, and runtime behavior.

Multi-language tree-sitter parser — supports ~50 languages including TypeScript, Python, PHP, Go, Rust, HTML, YAML, JSON, Markdown, Twig, SCSS, etc.

Structured code review — analyze code quality, security, architecture patterns, compare versions.

Open-source Cursor toolkit: local hooks, MCP server & sidebar extension for dialectical prompt and response oversight — privacy-first session quality.

Autopilot workflow — autonomous task execution with reasoning, context management, and shell commands.

MCP server for ng-forge dynamic forms - AI-assisted form schema generation

Batch execution patterns — run multiple operations sequentially, in parallel, or as a pipeline.

🏎️ The official FastMCP TypeScript library - build MCP servers and clients, fast 🏎️

Full project audit workflow — code quality review, security scan, architecture analysis, and metrics report.

Agent registry — register AI agents with capabilities, list available agents, query capabilities.

Session metrics tracking — token usage, costs, duration, and per-tool statistics.

Persistent key-value memory — store and recall information across sessions as JSON files.

In-memory file cache — avoid redundant disk reads with mtime-based invalidation.

MCP server that gives AI agents instant access to decompiled Java code from Maven dependencies. Blazing fast Java class analysis for Claude, Cursor, and other LLM-powered IDEs.

Knowledge base — index documents, search by content, fetch entries, purge stale data, rank by relevance.