YouTube Transcript MCP Server
This MCP server retrieves transcripts for given YouTube video URLs.
Tools
This MCP server provides the following tools:
get_transcript
Fetches the transcript of a specified YouTube video.
Parameters
- url (string): The full URL of the YouTube video. This field is required.
- lang (string, optional): The desired language for the transcript. Defaults to
enif not specified. - next_cursor (string, optional): Cursor to retrieve the next page of the transcript.
get_timed_transcript
Fetches the transcript of a specified YouTube video with timestamps..
Parameters
- url (string): The full URL of the YouTube video. This field is required.
- lang (string, optional): The desired language for the transcript. Defaults to
enif not specified. - next_cursor (string, optional): Cursor to retrieve the next page of the transcript.
get_video_info
Fetches the metadata of a specified YouTube video.
Parameters
- url (string): The full URL of the YouTube video. This field is required.
Installation
[!NOTE] You'll need
uvinstalled on your system to useuvxcommand.
For codename goose
Please refer to this tutorial for detailed installation instructions: YouTube Transcript Extension.
For Claude Desktop
Download the latest MCP bundle mcp-youtube-transcript.mcpb from
the Releases page,
then open the downloaded .mcpb file or drag it into the Claude Desktop's Settings window.
You can also manually configure this server for Claude Desktop.
Edit the claude_desktop_config.json file by adding the following entry under
mcpServers:
{
"mcpServers": {
"youtube-transcript": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/jkawamoto/mcp-youtube-transcript",
"mcp-youtube-transcript"
]
}
}
}
After editing, restart the application. For more information, see: For Claude Desktop Users - Model Context Protocol.
For LM Studio
To configure this server for LM Studio, click the button below.
Using Docker
A Docker image for this server is available on Docker Hub. Please refer to the Docker Hub page for detailed usage instructions and documentation.
Response Pagination
When retrieving transcripts for longer videos, the content may exceed the token size limits of the LLM.
To avoid this issue, this server splits transcripts that exceed 50,000 characters.
If a transcript is split, the response will include a next_cursor.
To retrieve the next part, include this next_cursor value in your request.
The token size limits vary depending on the LLM and language you are using.
If you need to split responses into smaller chunks,
you can adjust this using the --response-limit command line argument.
For example, the configuration below splits responses to contain no more than 15,000 characters each:
{
"mcpServers": {
"youtube-transcript": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/jkawamoto/mcp-youtube-transcript",
"mcp-youtube-transcript",
"--response-limit",
"15000"
]
}
}
}
Using Proxy Servers
In environments where access to YouTube is restricted, you can use proxy servers.
When using Webshare, set the username and password for the Residential Proxy using either
the environment variables WEBSHARE_PROXY_USERNAME and WEBSHARE_PROXY_PASSWORD,
or the command line arguments --webshare-proxy-username and --webshare-proxy-password.
When using other proxy servers, set the proxy server URL using either the environment variables HTTP_PROXY or
HTTPS_PROXY, or the command line arguments --http-proxy or --https-proxy.
For more details, please visit: Working around IP bans - YouTube Transcript API.
License
This application is licensed under the MIT License. See the LICENSE file for more details.