Skip to main content

Agent Skills MCP Server

Project description

Agent Skills MCP Server

MCP Server for Agent Skills.

Features

  • Dynamic Skill Discovery: Automatically discovers and loads skills from configurable directories
  • Environment-based Configuration: Configure skill search paths via environment variables
  • Global and Project-level Skills: Support for both system-wide and project-specific skills
  • YAML Frontmatter Validation: Validates skill metadata and structure
  • Duplicate Detection: Prevents duplicate tool names across different skill sources

Configuration

Environment Variables

Configure skill discovery paths using environment variables:

  • GLOBAL_SKILLS_PATH: Comma-separated list of global skill directories (default: ~/.skills/)
  • PROJECT_SKILLS_PATH: Comma-separated list of project-level skill directories (default: .skills/)

Example:

export GLOBAL_SKILLS_PATH="~/.skills/,~/.config/opencode/skills"
export PROJECT_SKILLS_PATH=".skills/,./.opencode/skills"

Default Paths

If no custom paths are configured, the server will search in these default locations:

  • ./.skills (project-level)
  • ~/.skills (global)

Usage

  1. Create skill directories in your configured paths
  2. Add SKILL.md files with YAML frontmatter to define your skills
  3. Start the MCP server: uv run main.py

Skill Format

Skills are defined in SKILL.md files with YAML frontmatter:

---
name: my-skill
description: Description of what this skill does (minimum 10 characters)
license: MIT
allowed_tools: ["tool1", "tool2"]
metadata:
  category: "utility"
---

# Skill Content

Your skill instructions and documentation go here.

Development

Copy .env.example to .env and customize the configuration:

cp .env.example .env

Run the development server:

uv run main.py

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

agent_skills_mcp_gkzhb-0.1.0-py3-none-any.whl (7.8 kB view details)

Uploaded Python 3

File details

Details for the file agent_skills_mcp_gkzhb-0.1.0-py3-none-any.whl.

File metadata

  • Download URL: agent_skills_mcp_gkzhb-0.1.0-py3-none-any.whl
  • Upload date:
  • Size: 7.8 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: uv/0.9.13 {"installer":{"name":"uv","version":"0.9.13"},"python":null,"implementation":{"name":null,"version":null},"distro":{"name":"macOS","version":null,"id":null,"libc":null},"system":{"name":null,"release":null},"cpu":null,"openssl_version":null,"setuptools_version":null,"rustc_version":null,"ci":null}

File hashes

Hashes for agent_skills_mcp_gkzhb-0.1.0-py3-none-any.whl
Algorithm Hash digest
SHA256 13fd16f82046fab7349098b223d7aace52a4044c45ef7c15cadf120f12a16d6b
MD5 355ab23e663364331c398f2287066607
BLAKE2b-256 3be3dfc7c3f9beca532202b3a2f85484952f50b91951261a10279485588b332a

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page