Enables AI models and coding assistants to semantically search and retrieve Claude Agent Skills using vector embeddings and the Model Context Protocol.
Sponsored
This MCP server brings Anthropic's powerful Agent Skills framework to the broader AI ecosystem, allowing any MCP-compatible AI model or coding assistant (like Cursor, Codex, or Gemini) to leverage specialized skills. It offers intelligent search capabilities by using vector embeddings for semantic similarity, implementing Anthropic's progressive disclosure architecture. This means skills are made available through multi-level loading, from metadata to full content and associated files, enhancing AI applications with curated scientific and official Claude skills without complex configuration.
主な機能
01Semantic Search for intelligent skill discovery
02Progressive Disclosure for multi-level skill loading
03Zero Configuration with curated skills out-of-the-box
04Multi-Source loading from GitHub repositories and local directories
05Fast & Local operation with automatic GitHub caching
069 GitHub stars
ユースケース
01Intelligently search for relevant skills based on task descriptions
02Retrieve specific skill files (scripts, data, references) from discovered skills
03Explore a complete inventory of all available Claude Agent Skills