Claude Skills MCP Server
by
Provides semantic vector search and progressive loading of Claude Agent Skills for any MCP‑compatible AI assistant.
Claude Skills MCP Server Overview
What is Claude Skills MCP Server about?
Enables AI assistants to discover and retrieve relevant Claude Agent Skills using embedded vectors and semantic similarity. The server follows the progressive disclosure pattern, initially returning lightweight metadata and loading full content or files only when requested.
How to use Claude Skills MCP Server?
- Cursor integration: Add the server to the Cursor directory or edit
~/.cursor/mcp.jsonwith the commanduvx claude-skills-mcp. - Standalone: Run
uvx claude-skills-mcpto start the lightweight frontend, which automatically downloads the heavier backend in the background. - Custom configuration: Generate a default config with
uvx claude-skills-mcp --example-config > config.json, modify it, then launch withuvx claude-skills-mcp --config config.json.
Key features
- Two‑package architecture: instant‑start frontend (~15 MB) + feature‑rich backend (~250 MB).
- Zero‑configuration out‑of‑the‑box loading of curated skill repositories (Anthropic official skills, K‑Dense scientific skills, and optional local directories).
- Semantic vector search powered by PyTorch and sentence‑transformers for intelligent skill discovery.
- Progressive disclosure: metadata → full skill content → individual files, reducing latency and avoiding Cursor timeouts.
- Fully local execution – no API keys required, with automatic GitHub caching.
- Configurable sources, model choices, and content size limits.
Use cases
- AI coding assistants: Quickly fetch specialized scripts, data processing utilities, or domain‑specific analysis tools.
- Scientific research bots: Retrieve bioinformatics or cheminformatics skills from the K‑Dense scientific collection.
- Enterprise knowledge bases: Expose curated internal tools as searchable skills for any MCP‑compatible platform.
- Rapid prototyping: Developers can explore the full inventory of available skills via the
list_skillstool.
FAQ
Q: Do I need an Anthropic API key? A: No. The server runs locally and uses pre‑computed embeddings; API keys are only required if you replace the embedding model with a hosted service.
Q: How long does the initial backend download take? A: Approximately 60‑120 seconds on a typical broadband connection; it runs in the background after the frontend starts.
Q: Can I add my own skill repositories? A: Yes. Edit the configuration file to include additional GitHub URLs or local paths; the backend will clone/cache them automatically.
Q: What Python version is required? A: Python 3.12 is the supported version.
Q: How do I update the server?
A: Re‑run the uvx claude-skills-mcp command; it will fetch the latest package versions from PyPI.
Claude Skills MCP Server's README
Claude Skills MCP Server
Use Claude's powerful new Skills system with ANY AI model or coding assistant - including Cursor, Codex, GPT-5, Gemini, and more. This MCP server brings Anthropic's Agent Skills framework to the entire AI ecosystem through the Model Context Protocol.
A Model Context Protocol (MCP) server that provides intelligent search capabilities for discovering relevant Claude Agent Skills using vector embeddings and semantic similarity. This server implements the same progressive disclosure architecture that Anthropic describes in their Agent Skills engineering blog, making specialized skills available to any MCP-compatible AI application.
An open-source project by K-Dense AI - creators of autonomous AI scientists for scientific research.
This MCP server enables any MCP-compatible AI assistant to intelligently search and retrieve skills from our curated Claude Scientific Skills repository and other skill sources like the Official Claude Skills.
Add to Cursor via Cursor Directory →
Demo
Semantic search and progressive loading of Claude Agent Skills in Cursor
Highlights
- Two-Package Architecture: Lightweight frontend (~15 MB) starts instantly; backend (~250 MB) downloads in background
- No Cursor Timeout: Frontend responds in <5 seconds, solving the timeout issue
- Semantic Search: Vector embeddings for intelligent skill discovery
- Progressive Disclosure: Multi-level skill loading (metadata → full content → files)
- Zero Configuration: Works out of the box with curated skills
- Multi-Source: Load from GitHub repositories and local directories
- Fast & Local: No API keys needed, with automatic GitHub caching
- Configurable: Customize sources, models, and content limits
Quick Start
For Cursor Users
Add through the Cursor Directory, or add to your Cursor config (~/.cursor/mcp.json):
{
"mcpServers": {
"claude-skills": {
"command": "uvx",
"args": ["claude-skills-mcp"]
}
}
}
The frontend starts instantly and displays tools, automatically downloading and starting the backend in the background (~60-120s due to RAG dependencies, one-time). Subsequent uses are instant.
Using uvx (Standalone)
Run the server with default configuration:
uvx claude-skills-mcp
This starts the lightweight frontend which auto-downloads the backend and loads ~90 skills from Anthropic's official skills repository and K-Dense AI's scientific skills collection.
With Custom Configuration
# 1. Print the default configuration
uvx claude-skills-mcp --example-config > config.json
# 2. Edit config.json to your needs
# 3. Run with your custom configuration
uvx claude-skills-mcp --config config.json
Documentation
- Getting Started - Installation, Cursor setup, CLI usage, and troubleshooting
- Architecture Guide - Two-package design, data flow, and components
- API Documentation - Tool parameters, examples, and best practices
- Usage Examples - Advanced configuration, real-world use cases, and custom skill creation
- Testing Guide - Complete testing instructions, CI/CD, and coverage analysis
MCP Tools
The server provides three tools for working with Claude Agent Skills:
search_skills- Semantic search for relevant skills based on task descriptionread_skill_document- Retrieve specific files (scripts, data, references) from skillslist_skills- View complete inventory of all loaded skills (for exploration/debugging)
See API Documentation for detailed parameters, examples, and best practices.
Architecture (v1.0.0)
The system uses a two-package architecture for optimal performance:
-
Frontend (
claude-skills-mcp): Lightweight proxy (~15 MB)- Starts instantly (<5 seconds) ✅ No Cursor timeout!
- Auto-downloads backend on first use
- MCP server (stdio) for Cursor
-
Backend (
claude-skills-mcp-backend): Heavy server (~250 MB)- Vector search with PyTorch & sentence-transformers
- MCP server (streamable HTTP)
- Auto-installed by frontend OR deployable standalone
Benefits:
- ✅ Solves Cursor timeout issue (frontend starts instantly)
- ✅ Same simple user experience (
uvx claude-skills-mcp) - ✅ Backend downloads in background (doesn't block Cursor)
- ✅ Can connect to remote hosted backend (no local install needed)
See Architecture Guide for detailed design and data flow.
Skill Sources
Load skills from GitHub repositories (direct skills or Claude Code plugins) or local directories.
By default, loads from:
- Official Anthropic Skills - 15 diverse skills for documents, presentations, web artifacts, and more
- K-Dense AI Scientific Skills - 78+ specialized skills for bioinformatics, cheminformatics, and scientific analysis
- Local directory
~/.claude/skills(if it exists)
Contributing
Contributions are welcome! To contribute:
- Report issues: Open an issue for bugs or feature requests
- Submit PRs: Fork, create a feature branch, ensure tests pass (
uv run pytest tests/), then submit - Code style: Run
uvx ruff check src/before committing - Add tests: New features should include tests
Development
Version Management: This monorepo uses a centralized version system:
- Edit the
VERSIONfile at the repo root to bump the version - Run
python3 scripts/sync-version.pyto sync all references (or use--checkto verify) - The
scripts/build-all.shscript automatically syncs versions before building
For questions, email orion.li@k-dense.ai
Learn More
- Agent Skills Documentation - Official Anthropic documentation on the Skills format
- Agent Skills Blog Post - Announcement and overview
- Model Context Protocol - The protocol that makes cross-platform Skills possible
- Engineering Blog: Equipping Agents for the Real World - Technical deep-dive on the Skills architecture
License
This project is licensed under the Apache License 2.0.
Copyright 2025 K-Dense AI (https://k-dense.ai)
Claude Skills MCP Server Reviews
Login Required
Please log in to share your review and rating for this MCP.
Actions
Claude Skills MCP Server's Information
- Author
- K-Dense-AI
- Category
- Search
- Language
- Python
- License
- Apache License 2.0
- Stars
- 53
- Updated
- 3 days ago
Similar MCP Servers like Claude Skills MCP Server
Explore related MCPs that share similar capabilities and solve comparable challenges
Exa MCP Server
by exa-labs
Provides real-time web search capabilities to AI assistants via a Model Context Protocol server, enabling safe and controlled access to the Exa AI Search API.
Perplexity Ask
by perplexityai
Enables Claude and other MCP‑compatible applications to perform real‑time web searches through the Perplexity (Sonar) API without leaving the MCP ecosystem.
Microsoft Learn MCP Server
by MicrosoftDocs
Provides semantic search and fetch capabilities for Microsoft official documentation, returning content in markdown format via a lightweight streamable HTTP transport for AI agents and development tools.
Elasticsearch MCP Server
by elastic
Enables natural‑language interaction with Elasticsearch indices via the Model Context Protocol, exposing tools for listing indices, fetching mappings, performing searches, running ES|QL queries, and retrieving shard information.
Graphlit MCP Server
by graphlit
Enables integration between MCP clients and the Graphlit platform, providing ingestion, extraction, retrieval, and RAG capabilities across a wide range of data sources and connectors.
Everything Search
by mamertofabian
Fast cross‑platform file searching leveraging the Everything SDK on Windows, Spotlight on macOS, and locate/plocate on Linux.
Elasticsearch OpenSearch MCP Server
by cr7258
Provides Elasticsearch and OpenSearch interaction via Model Context Protocol, enabling document search, index management, cluster monitoring, and alias operations.
Kagi MCP Server
by kagisearch
Provides web search and video summarization capabilities through the Model Context Protocol, enabling AI assistants like Claude to perform queries and summarizations.
MCP Compass
by liuyoshio
Provides natural‑language search and recommendation for Model Context Protocol servers, delivering rich metadata and real‑time updates.