mcp-youtube-transcript — Claude Code MCP server: setup guide
MCP server that retrieves YouTube video transcripts, timed segments, and metadata for AI agents. It splits long transcripts into chunks to protect the LLM context window.
Open on GitHubWhat mcp-youtube-transcript does
The server exposes four tools for client workflows: get_transcript, get_timed_transcript, get_available_languages, and get_video_info. Models can read complete video transcripts, fetch timestamped intervals, or inspect channel details and video titles. The optional lang parameter specifies preferred subtitle languages.
To prevent context window overflow, responses exceeding 50,000 characters are broken into chunks. The tool returns a next_cursor token so the agent can request subsequent sections on demand. Passing --response-limit adjusts this character boundary, and setting it to -1 disables chunking entirely. The server also supports residential proxies like Webshare or ScrapingAnt to bypass YouTube IP restrictions.
Running the server through uvx requires having uv installed on the host system.
What it helps with
- Fetch raw text transcripts from YouTube video links
- Extract subtitle segments with start timestamps and duration values
- Check manual and generated subtitle languages for a video
- Handle long transcripts in chunks using cursor pagination
- Route requests through residential proxies to prevent IP rate limits
Example prompts for the agent
- Extract the full text transcript for
<url>. - Get the timed transcript with timestamps for
<url>in English. - Show all available subtitle languages for
<url>.
How to install mcp-youtube-transcript
Install
The MCP registry has no launch command for it: see the repository README
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about mcp-youtube-transcript
How do you install mcp-youtube-transcript?
Add the entry to your client's MCP configuration under mcpServers using command uvx with arguments --from, git+https://github.com/jkawamoto/mcp-youtube-transcript, and mcp-youtube-transcript. Ensure uv is installed on your machine.
What does mcp-youtube-transcript do?
It extracts transcripts, timestamped intervals, and video details from YouTube URLs. It also handles long videos through chunking and supports proxy credentials to avoid IP blocks.
How do you disable transcript pagination?
Pass --response-limit with a negative number such as -1 in the server arguments. Any positive value changes the chunk size from the default 50,000 characters.
