Repository avatar
AI Tools
v0.2.0
active

fetchtranscript

com.fetchtranscript/fetchtranscript

YouTube transcripts, video metadata, chapters, comments, channels and search for AI assistants.

Documentation

FetchTranscript MCP Server

mcptry

An MCP server that gives AI assistants (Claude Desktop, Cursor, etc.) access to YouTube transcripts, video metadata, channels, and search via the FetchTranscript API.

No install: connect from Claude.ai or ChatGPT

FetchTranscript also runs as a remote MCP server with OAuth sign-in, so you can use the same tools from Claude.ai, Claude Desktop and mobile, ChatGPT or any client that supports remote servers, without an API key or anything to install:

https://api.fetchtranscript.com/mcp
  • Claude: Customize → Connectors → + Add → Add custom connector, paste the URL, then sign in with your FetchTranscript account and allow access.
  • ChatGPT: chatgpt.com/plugins → + → Add custom MCP server, paste the URL as Server URL, OAuth authentication.
  • Claude Code: claude mcp add --transport http fetchtranscript https://api.fetchtranscript.com/mcp

Calls use your account's credits exactly like the API. Step-by-step guide: https://fetchtranscript.com/docs/mcp. The package below is the local server (stdio, API key), for developers who prefer to run it themselves; both offer the same tools, prompts and resources.

Features

8 Tools — get transcripts, list languages, video metadata, chapters, comments, channel info, channel videos, search

4 Documentation Resources — API reference, quickstart guide, pricing, workflow examples

3 Prompt Templates — summarize video, compare videos, extract quotes

Quick Start

1. Get an API Key

Sign up at fetchtranscript.com and create an API key from the dashboard.

2. Configure Claude Desktop

Add to your claude_desktop_config.json:

{
  "mcpServers": {
    "fetchtranscript": {
      "command": "uvx",
      "args": ["fetchtranscript-mcp"],
      "env": {
        "FETCHTRANSCRIPT_API_KEY": "yt_your_key_here"
      }
    }
  }
}

3. Use it

Ask Claude:

  • "Get the transcript of YouTube video dQw4w9WgXcQ"
  • "Summarize this YouTube video: https://youtube.com/watch?v=..."
  • "Search YouTube for 'machine learning explained' and summarize the top result"

Configuration for Other Clients

Cursor

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "fetchtranscript": {
      "command": "uvx",
      "args": ["fetchtranscript-mcp"],
      "env": {
        "FETCHTRANSCRIPT_API_KEY": "yt_your_key_here"
      }
    }
  }
}

Claude Code

claude mcp add fetchtranscript -- uvx fetchtranscript-mcp

Set FETCHTRANSCRIPT_API_KEY in your environment.

Installation Alternatives

pip

pip install fetchtranscript-mcp
FETCHTRANSCRIPT_API_KEY=yt_xxx fetchtranscript-mcp

npx

FETCHTRANSCRIPT_API_KEY=yt_xxx npx fetchtranscript-mcp

Tools

ToolDescriptionKey defaults
get_transcriptFetch video transcriptformat=text
list_languagesAvailable transcript languages—
get_video_metadataVideo title, views, likes, etc.—
get_chaptersVideo chapter list—
get_commentsTop commentslimit=20
get_channel_infoChannel metadata—
list_channel_videosVideos from a channellimit=10
search_videosSearch YouTubelimit=5

Environment Variables

VariableRequiredDescription
FETCHTRANSCRIPT_API_KEYYesYour API key (starts with yt_)
FETCHTRANSCRIPT_BASE_URLNoOverride API base URL (default: https://api.fetchtranscript.com)

Development

cd mcp
pip install -e ".[dev]"
pytest tests/

Test with MCP Inspector:

FETCHTRANSCRIPT_API_KEY=yt_xxx mcp dev src/fetchtranscript_mcp/server.py

License

MIT

PYPI
fetchtranscript-mcp
Install Command
pip install fetchtranscript-mcp