Skills MCP

Transform any AI agent into a domain expert by giving it access to modular, reusable skills through the Model Context Protocol.

Inspired by Claude Skills: This MCP server brings Claude's Skills pattern to any MCP-compatible agent.

What: An MCP server that brings Claude's Skills format to any MCP-compatible agent
Why: Create skills once, use them everywhere—across Claude, VS Code, Cursor, and any MCP tool
How: Point the server at your skills directory and agents discover them automatically

Quick Setup

The fastest way to get started is with npx. Choose your platform:

Claude Code

Create .mcp.json in your project or ~/.claude.json globally:

{
  "mcpServers": {
    "skills-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "skills-mcp", "-s", "/absolute/path/to/skills"]
    }
  }
}

Claude for Desktop

Create ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "skills-mcp": {
      "command": "npx",
      "args": ["-y", "skills-mcp", "-s", "/absolute/path/to/skills"]
    }
  }
}

Cursor

Create .cursor/mcp.json in your project or ~/.cursor/mcp.json globally:

{
  "mcpServers": {
    "skills-mcp": {
      "command": "npx",
      "args": ["-y", "skills-mcp", "-s", "/absolute/path/to/skills"]
    }
  }
}

VS Code

Create .vscode/mcp.json in your project:

{
  "servers": {
    "skills-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "skills-mcp", "-s", "/absolute/path/to/skills"]
    }
  }
}

Replace /absolute/path/to/skills with your actual skills directory path.

Try It Out

Start the MCP server in your agent
Recommended: Run the /init-skills prompt at the start of each session to provide background guidance on the Skills MCP workflow
Alternative: Simply ask the agent to complete a task—it will discover and use skills when needed

That's it! Your agent can now discover and use skills.

Get Example Skills

Want to try it out with ready-made skills? Anthropic maintains a collection of example skills that you can bring into your project instantly using npx degit:

# Get the skill creator skill
npx degit anthropics/skills/skill-creator skills/skill-creator

# Get the MCP builder skill
npx degit anthropics/skills/mcp-builder skills/mcp-builder

These commands will download the skills directly into your skills/ directory without any git history. Browse the Anthropic skills repository to see all available examples.

Agent Instructions Setup

Want Skills MCP guidance always available in your agent's context? Export the instructions:

Recommended: Use AGENTS.md for broad agent support:

npx -y skills-mcp instructions >> AGENTS.md

For agents without AGENTS.md support:

# Claude Code
npx -y skills-mcp instructions >> CLAUDE.md

When to Use Instructions File vs `/init-skills` Prompt

Use instructions export if you want skills guidance always present in every conversation
Use /init-skills prompt if you want to minimize context usage and only load guidance when needed

Both approaches use the same content—choose based on your preference for context management.

Understanding Skills

What are Skills?

Skills are modular, self-contained packages that transform general-purpose AI agents into specialized experts. Think of them as "onboarding guides" for specific domains or tasks—they provide procedural knowledge that no model can fully possess.

Example: A PDF Processing Skill might include:

Instructions for extracting text and filling forms
Python scripts for reliable PDF operations
Reference documentation for advanced use cases
Template files for generating documents

Instead of explaining PDF processing in every conversation, you install the skill once and the agent knows when and how to use it.

Why Skills MCP?

While Claude has native Skills support built-in, this MCP server brings that same capability to other agents:

Universal compatibility: Any MCP-compatible agent can now use Claude Skills
Unified management: Single skills directory works across all agents and platforms
Optional for Claude: When using Claude Desktop or Claude Code, you can disable this server and use native Skills instead
Progressive disclosure: Skills load information in stages, minimizing context usage

Key benefit: Create skills once in Claude's format, use them everywhere—whether with Claude's native support or via MCP in VS Code, Cursor, and other tools.

How Skills Work

Skills use a three-level progressive disclosure system to manage context efficiently:

Metadata (~100 tokens): Name and description loaded at startup
Instructions (~5k tokens): Main SKILL.md content loaded when skill is triggered
Resources (loaded as needed): References, scripts, and assets accessed on-demand

This means you can install dozens of skills without context penalty—agents only load what they need, when they need it.

Creating Skills

Quick Start: Basic Skill Structure

Skills follow Anthropic's convention-based format from Claude Skills:

skill-name/
├── SKILL.md              # Required: Skill metadata and instructions
├── references/           # Optional: Documentation loaded as needed
├── scripts/              # Optional: Executable code
└── assets/               # Optional: Templates and files for output

SKILL.md Format

---
name: Skill Name
description: What this skill does and when to use it (be specific!)
---

# Skill Name

## Instructions

[Step-by-step guidance for the agent]

## Examples

[Concrete usage examples]

Tips for writing good skills:

Make descriptions specific about WHEN to use the skill
Use imperative/infinitive form in instructions ("To do X, use Y")
Keep SKILL.md under 5k words; move detailed docs to references/
Bundle scripts for deterministic operations
Include templates in assets/ for files used in output

For more details, see the Skills specification.

Advanced Usage

Command Line Options

Arguments

-s, --skills-dir: Path to skills directory (required, can be specified multiple times, must be absolute paths)

Multiple Skills Directories

When specifying multiple skills directories, all directories are scanned for skills. If multiple skills with the same ID are found across different directories, a warning will be logged and the last loaded skill will be used.

Example configuration with multiple directories:

{
  "servers": {
    "skills-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "skills-mcp",
        "-s",
        "/path/to/skills1",
        "-s",
        "/path/to/skills2"
      ]
    }
  }
}

Testing the Server

You can test the server manually using stdio:

npx skills-mcp --skills-dir /absolute/path/to/skills

The server will start and wait for JSON-RPC messages on stdin. Press Ctrl+C to stop the server.

Security Considerations

⚠️ Important: Skills provide agents with instructions and executable code. Only use skills from trusted sources—those you created yourself or obtained from Anthropic.

A malicious skill can:

Direct agents to invoke tools in harmful ways
Execute code with the agent's privileges
Access or expose sensitive data

Treat skills like software installation: Only install from trusted sources, especially in production systems with access to sensitive data or critical operations.

For more details, see the Security Considerations section in the spec.

API Reference

Available Tools

`list_skills`

Lists all available skills with their metadata.

Output:

{
  "skills": [
    {
      "id": "pdf-processing",
      "name": "PDF Processing",
      "description": "Extract text and tables from PDF files..."
    }
  ]
}

`get_skill`

Retrieves the full skill content and absolute path.

Input:

{
  "id": "pdf-processing"
}

Output:

{
  "path": "/Users/username/.claude/skills/pdf-processing/SKILL.md",
  "name": "PDF Processing",
  "description": "Extract text and tables...",
  "content": "# PDF Processing\n\n## Quick start\n..."
}

Available Prompts

`init-skills`

Provides informational guidance about the Skills MCP workflow. This prompt:

Explains what skills are and how they're structured
Outlines the progressive disclosure model (load only what you need, when you need it)
Describes the step-by-step workflow for discovering, loading, and using skills
Clarifies that the MCP is a minimal wrapper—agents handle all file operations

When to use: Run at the start of a conversation to provide background context. The prompt is informational only—it doesn't trigger any immediate actions. Agents will use skills when they encounter tasks that match available skill descriptions.

How It Works

The Skills MCP follows a minimal wrapper design that leverages the full capabilities of modern AI agents:

What the server provides:

Skill discovery and metadata
Skill content with absolute file paths
Skills-specific context formatting

What agents handle (using their existing tools):

Reading referenced files (references/, scripts/, assets/)
Executing scripts
Searching and navigating directories

Example workflow:

Agent calls list_skills and finds "PDF Processing"
Agent calls get_skill and receives /path/to/pdf-processing/SKILL.md
Skill mentions references/FORMS.md for advanced features
Agent constructs full path and reads it: /path/to/pdf-processing/references/FORMS.md
Agent executes scripts: cd /path/to/pdf-processing && python scripts/fill_form.py

This design keeps the MCP server simple while giving agents maximum flexibility.

Learn More

Claude Skills: The original Skills format this server implements
Full Specification: Complete technical specification and design rationale
Model Context Protocol: Learn about MCP

Skills MCP

Transform any AI agent into a domain expert by giving it access to modular, reusable skills through the Model Context Protocol.

Inspired by Claude Skills: This MCP server brings Claude's Skills pattern to any MCP-compatible agent.

What: An MCP server that brings Claude's Skills format to any MCP-compatible agent
Why: Create skills once, use them everywhere—across Claude, VS Code, Cursor, and any MCP tool
How: Point the server at your skills directory and agents discover them automatically

Quick Setup

The fastest way to get started is with npx. Choose your platform:

Claude Code

Create .mcp.json in your project or ~/.claude.json globally:

{
  "mcpServers": {
    "skills-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "skills-mcp", "-s", "/absolute/path/to/skills"]
    }
  }
}

Claude for Desktop

Create ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "skills-mcp": {
      "command": "npx",
      "args": ["-y", "skills-mcp", "-s", "/absolute/path/to/skills"]
    }
  }
}

Cursor

Create .cursor/mcp.json in your project or ~/.cursor/mcp.json globally:

{
  "mcpServers": {
    "skills-mcp": {
      "command": "npx",
      "args": ["-y", "skills-mcp", "-s", "/absolute/path/to/skills"]
    }
  }
}

VS Code

Create .vscode/mcp.json in your project:

{
  "servers": {
    "skills-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "skills-mcp", "-s", "/absolute/path/to/skills"]
    }
  }
}

Replace /absolute/path/to/skills with your actual skills directory path.

Try It Out

Start the MCP server in your agent
Recommended: Run the /init-skills prompt at the start of each session to provide background guidance on the Skills MCP workflow
Alternative: Simply ask the agent to complete a task—it will discover and use skills when needed

That's it! Your agent can now discover and use skills.

Get Example Skills

Want to try it out with ready-made skills? Anthropic maintains a collection of example skills that you can bring into your project instantly using npx degit:

# Get the skill creator skill
npx degit anthropics/skills/skill-creator skills/skill-creator

# Get the MCP builder skill
npx degit anthropics/skills/mcp-builder skills/mcp-builder

These commands will download the skills directly into your skills/ directory without any git history. Browse the Anthropic skills repository to see all available examples.

Agent Instructions Setup

Want Skills MCP guidance always available in your agent's context? Export the instructions:

Recommended: Use AGENTS.md for broad agent support:

npx -y skills-mcp instructions >> AGENTS.md

For agents without AGENTS.md support:

# Claude Code
npx -y skills-mcp instructions >> CLAUDE.md

When to Use Instructions File vs `/init-skills` Prompt

Use instructions export if you want skills guidance always present in every conversation
Use /init-skills prompt if you want to minimize context usage and only load guidance when needed

Both approaches use the same content—choose based on your preference for context management.

Understanding Skills

What are Skills?

Example: A PDF Processing Skill might include:

Instructions for extracting text and filling forms
Python scripts for reliable PDF operations
Reference documentation for advanced use cases
Template files for generating documents

Instead of explaining PDF processing in every conversation, you install the skill once and the agent knows when and how to use it.

Why Skills MCP?

While Claude has native Skills support built-in, this MCP server brings that same capability to other agents:

Universal compatibility: Any MCP-compatible agent can now use Claude Skills
Unified management: Single skills directory works across all agents and platforms
Optional for Claude: When using Claude Desktop or Claude Code, you can disable this server and use native Skills instead
Progressive disclosure: Skills load information in stages, minimizing context usage

Key benefit: Create skills once in Claude's format, use them everywhere—whether with Claude's native support or via MCP in VS Code, Cursor, and other tools.

How Skills Work

Skills use a three-level progressive disclosure system to manage context efficiently:

Metadata (~100 tokens): Name and description loaded at startup
Instructions (~5k tokens): Main SKILL.md content loaded when skill is triggered
Resources (loaded as needed): References, scripts, and assets accessed on-demand

This means you can install dozens of skills without context penalty—agents only load what they need, when they need it.

Creating Skills

Quick Start: Basic Skill Structure

Skills follow Anthropic's convention-based format from Claude Skills:

skill-name/
├── SKILL.md              # Required: Skill metadata and instructions
├── references/           # Optional: Documentation loaded as needed
├── scripts/              # Optional: Executable code
└── assets/               # Optional: Templates and files for output

SKILL.md Format

---
name: Skill Name
description: What this skill does and when to use it (be specific!)
---

# Skill Name

## Instructions

[Step-by-step guidance for the agent]

## Examples

[Concrete usage examples]

Tips for writing good skills:

Make descriptions specific about WHEN to use the skill
Use imperative/infinitive form in instructions ("To do X, use Y")
Keep SKILL.md under 5k words; move detailed docs to references/
Bundle scripts for deterministic operations
Include templates in assets/ for files used in output

For more details, see the Skills specification.

Advanced Usage

Command Line Options

Arguments

-s, --skills-dir: Path to skills directory (required, can be specified multiple times, must be absolute paths)

Multiple Skills Directories

Example configuration with multiple directories:

{
  "servers": {
    "skills-mcp": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "skills-mcp",
        "-s",
        "/path/to/skills1",
        "-s",
        "/path/to/skills2"
      ]
    }
  }
}

Testing the Server

You can test the server manually using stdio:

npx skills-mcp --skills-dir /absolute/path/to/skills

The server will start and wait for JSON-RPC messages on stdin. Press Ctrl+C to stop the server.

Security Considerations

⚠️ Important: Skills provide agents with instructions and executable code. Only use skills from trusted sources—those you created yourself or obtained from Anthropic.

A malicious skill can:

Direct agents to invoke tools in harmful ways
Execute code with the agent's privileges
Access or expose sensitive data

Treat skills like software installation: Only install from trusted sources, especially in production systems with access to sensitive data or critical operations.

For more details, see the Security Considerations section in the spec.

API Reference

Available Tools

`list_skills`

Lists all available skills with their metadata.

Output:

{
  "skills": [
    {
      "id": "pdf-processing",
      "name": "PDF Processing",
      "description": "Extract text and tables from PDF files..."
    }
  ]
}

`get_skill`

Retrieves the full skill content and absolute path.

Input:

{
  "id": "pdf-processing"
}

Output:

{
  "path": "/Users/username/.claude/skills/pdf-processing/SKILL.md",
  "name": "PDF Processing",
  "description": "Extract text and tables...",
  "content": "# PDF Processing\n\n## Quick start\n..."
}

Available Prompts

`init-skills`

Provides informational guidance about the Skills MCP workflow. This prompt:

Explains what skills are and how they're structured
Outlines the progressive disclosure model (load only what you need, when you need it)
Describes the step-by-step workflow for discovering, loading, and using skills
Clarifies that the MCP is a minimal wrapper—agents handle all file operations

How It Works

The Skills MCP follows a minimal wrapper design that leverages the full capabilities of modern AI agents:

What the server provides:

Skill discovery and metadata
Skill content with absolute file paths
Skills-specific context formatting

What agents handle (using their existing tools):

Reading referenced files (references/, scripts/, assets/)
Executing scripts
Searching and navigating directories

Example workflow:

Agent calls list_skills and finds "PDF Processing"
Agent calls get_skill and receives /path/to/pdf-processing/SKILL.md
Skill mentions references/FORMS.md for advanced features
Agent constructs full path and reads it: /path/to/pdf-processing/references/FORMS.md
Agent executes scripts: cd /path/to/pdf-processing && python scripts/fill_form.py

This design keeps the MCP server simple while giving agents maximum flexibility.

Learn More

Claude Skills: The original Skills format this server implements
Full Specification: Complete technical specification and design rationale
Model Context Protocol: Learn about MCP

Skills MCP

Skills MCP

Quick Setup

Try It Out

Get Example Skills

Agent Instructions Setup

When to Use Instructions File vs /init-skills Prompt

Understanding Skills

Creating Skills

SKILL.md Format

Advanced Usage

Arguments

Multiple Skills Directories

Testing the Server

API Reference

list_skills

get_skill

init-skills

Learn More

Skills MCP

Quick Setup

Try It Out

Get Example Skills

Agent Instructions Setup

When to Use Instructions File vs /init-skills Prompt

Understanding Skills

Creating Skills

SKILL.md Format

Advanced Usage

Arguments

Multiple Skills Directories

Testing the Server

API Reference

list_skills

get_skill

init-skills

Learn More

When to Use Instructions File vs `/init-skills` Prompt

`list_skills`

`get_skill`

`init-skills`

When to Use Instructions File vs `/init-skills` Prompt

`list_skills`

`get_skill`

`init-skills`