agent-skills-mcp

agent-skills-mcp

Loads Agent Skills from markdown files, exposing them as MCP tools or system prompts for AI agents.

Category
Visit Server

README

agent-skills-mcp - Load Agent Skills for your agents

PyPI - Version Codecov

[!WARNING] This Python implementation is deprecated. Please use the Rust implementation instead: https://github.com/DiscreteTom/agent-skills-mcp-rs

Usage

Full CLI Usage

<details>

<summary><code>uvx agent-skills-mcp --help</code></summary>

 Usage: agent-skills-mcp [OPTIONS]

 Agent Skills MCP - Load Agent Skills for your agents

╭─ Options ──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╮
│ --skill-folder  TEXT                  Path to folder containing skill markdown files [env var: SKILL_FOLDER] [default: skills] │
│ --mode          [tool|system_prompt]  Operating mode [env var: MODE] [default: tool]                                           │
│ --version                             Show version and exit                                                                    │
│ --help                                Show this message and exit.                                                              │
╰────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯

</details>

Setup

First, put your skills in ~/skills, e.g.

git clone https://github.com/anthropics/skills.git ~/skills

The server recursively searches for SKILL.md files and follows symlinks, allowing flexible skill organization.

Then, add this to your MCP client configuration:

Install MCP Server Add to Kiro

{
  "mcpServers": {
    "skills": {
      "command": "uvx",
      "args": ["agent-skills-mcp"],
      "env": {
        "SKILL_FOLDER": "~/skills"
      }
    }
  }
}

Modes

  • system_prompt: Include skill information in MCP instructions (recommended if your agent regards MCP server instructions)
  • tool: Register skills as MCP tools (fallback mode since many agents ignore MCP server instructions)

CHANGELOG

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured