miduconf
🚀 Mi demos de la Miduconf 2025 👾
claude mcp add --transport stdio 0gis0-miduconf-mcp node dist/index.js \ --env YOUTUBE_API_KEY="Your YouTube API key (set in .env or YOUTUBE_API_KEY)"
How to use
This MCP server exposes a set of YouTube-related tools implemented in a modular fashion. The server is written in TypeScript and compiles to JavaScript under dist, and it registers a collection of tools (for example, search_videos and search_playlists) that a language model or client can invoke via the MCP protocol. The codebase demonstrates how to structure tools as small functions that receive the server instance and register themselves with registerTool, enabling the model to request video searches, playlist searches, and related YouTube data through well-defined, safe tool boundaries. To interact with the server, you typically run the built server locally and connect a suitable MCP client (such as the official inspector) over stdio. The README also shows how to configure the server for VS Code integration and how to test the tools manually.
How to install
Prerequisites:
- Node.js (LTS) and npm installed on your system
- Git installed
- Clone the repository:
git clone https://github.com/0GiS0/0gis0-miduconf-mcp.git
cd miduconf
- Install dependencies:
npm install
- Build the MCP server (TypeScript to JavaScript in dist):
npm run build
- Run the MCP server locally:
node dist/index.js
- Optional: test with the MCP Inspector client:
npx @modelcontextprotocol/inspector
- If you register API keys or environment variables, create an .env file or set them in your environment. For example, the server expects a YouTube API key to access certain tools.
# Example .env
YOUTUBE_API_KEY=your_youtube_api_key_here
- If you modify the code, re-run the build step to update dist:
npm run build
Additional notes
Tips and caveats:
- The server uses stdio transport by default, so tools are exposed through the MCP protocol rather than a web API.
- You can add more YouTube-related tools by following the pattern in src/tools/youtube (e.g., searchVideos, searchPlaylists) and registering them from the appropriate index.ts file.
- Ensure you copy .env-sample to .env and set your API keys (as indicated in the README) if you rely on external APIs.
- The configuration example in this documentation uses a single MCP server named miduconf; you can expand with additional servers by adding more entries under mcpServers.
- The npm package name is not specified in this repository; if you publish it, specify the package name in npm_package. Otherwise this field remains null.
Related MCP Servers
context7
Context7 MCP Server -- Up-to-date code documentation for LLMs and AI code editors
obsidian -tools
Add Obsidian integrations like semantic search and custom Templater prompts to Claude or any MCP client.
MiniMax -JS
Official MiniMax Model Context Protocol (MCP) JavaScript implementation that provides seamless integration with MiniMax's powerful AI capabilities including image generation, video generation, text-to-speech, and voice cloning APIs.
mcp-bundler
Is the MCP configuration too complicated? You can easily share your own simplified setup!
akyn-sdk
Turn any data source into an MCP server in 5 minutes. Build AI-agents-ready knowledge bases.
promptboard
The Shared Whiteboard for Your AI Agents via MCP. Paste screenshots, mark them up, and share with AI.