YouTube
An MCP server for interacting with YouTube's data and services.
Youtube MCP server
About
The server is a bridge between the Youtube API and the AI assistants and is based on the Model Context Protocol.
What is MCP?
The Model Context Protocol (MCP) is a system that lets AI apps, like Claude Desktop, connect to external tools and data sources. It gives a clear and safe way for AI assistants to work with local services and APIs while keeping the user in control.
What does this server do?
- Download closed captions for the given video
Practical use cases
- Create a summary of the video
Prerequisites
Installation
uv tool install git+https://github.com/sparfenyuk/mcp-youtube
[!NOTE] If you have already installed the server, you can update it using
uv tool upgrade --reinstallcommand.
[!NOTE] If you want to delete the server, use the
uv tool uninstall mcp-youtubecommand.
Configuration
Claude Desktop Configuration
Configure Claude Desktop to recognize the Youtube MCP server.
-
Open the Claude Desktop configuration file:
- in MacOS, the configuration file is located at
~/Library/Application Support/Claude/claude_desktop_config.json - in Windows, the configuration file is located at
%APPDATA%\Claude\claude_desktop_config.json
Note: You can also find claude_desktop_config.json inside the settings of Claude Desktop app
- in MacOS, the configuration file is located at
-
Add the server configuration
{ "mcpServers": { "mcp-youtube": { "command": "mcp-youtube", } } } }
Development
Getting started
-
Clone the repository
-
Install the dependencies
uv sync -
Run the server
uv run mcp-youtube --help
Tools can be added to the src/mcp_youtube/tools.py file.
How to add a new tool:
-
Create a new class that inherits from ToolArgs
class NewTool(ToolArgs): """Description of the new tool.""" passAttributes of the class will be used as arguments for the tool. The class docstring will be used as the tool description.
-
Implement the tool_runner function for the new class
@tool_runner.register async def new_tool(args: NewTool) -> t.Sequence[TextContent | ImageContent | EmbeddedResource]: passThe function should return a sequence of TextContent, ImageContent or EmbeddedResource. The function should be async and accept a single argument of the new class.
-
Done! Restart the client and the new tool should be available.
Validation can accomplished either through Claude Desktop or by running the tool directly.
Debugging the server in the Inspector
The MCP inspector is a tool that helps to debug the server using fancy UI. To run it, use the following command:
npx @modelcontextprotocol/inspector uv run mcp-youtube
Troubleshooting
Message 'Could not connect to MCP server mcp-youtube'
If you see the message 'Could not connect to MCP server mcp-youtube' in Claude Desktop, it means that the server configuration is incorrect.
Try the following:
- Use the full path to the
mcp-youtubebinary in the configuration file
Related Servers
Weather MCP Server
Provides weather information using the OpenWeatherMap API.
LlamaCloud
Connect to and manage data indexes on the LlamaCloud platform.
Vanta MCP Server
A server for interacting with Vanta's security compliance platform.
Ntropy MCP server
Enrich banking data using the Ntropy API.
Cloudflare Remote MCP Server (Authless)
Deploy a remote, authentication-free MCP server on Cloudflare Workers or locally via npm.
Bybit API
An interface to interact with the Bybit cryptocurrency exchange API.
AWS Application Signals
Interact with AWS Application Signals for application monitoring and troubleshooting. Requires AWS credentials.
Amazon Nova Reel 1.1
An MCP server for generating videos using Amazon Nova Reel 1.1 via AWS Bedrock.
Amazon VPC Lattice
Access and manage AWS VPC Lattice resources and related documentation.
Rostro
Turn any language model into a multimodal powerhouse that can generate images, music, videos and more on the fly. Rostro's tools are designed to be used by language models from the ground up, expanding capabilities with minimal context bloat.