FetchTranscript

● Active

com.fetchtranscript/fetchtranscript

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

Connect this server

One click to install, or copy the config below. Suits: Claude Desktop · Cursor.

Add to Cursor Add to VS CodeClaude Desktop / Claude Code: paste the config below.

Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):

{
  "mcpServers": {
    "fetchtranscript": {
      "command": "uvx",
      "args": [
        "fetchtranscript-mcp"
      ],
      "env": {
        "FETCHTRANSCRIPT_API_KEY": "<your FETCHTRANSCRIPT_API_KEY>"
      }
    }
  }
}
One line, from the terminal
Claude Code
claude mcp add --env FETCHTRANSCRIPT_API_KEY='<your FETCHTRANSCRIPT_API_KEY>' --transport stdio fetchtranscript -- uvx fetchtranscript-mcp
OpenAI Codex CLI
codex mcp add fetchtranscript --env FETCHTRANSCRIPT_API_KEY='<your FETCHTRANSCRIPT_API_KEY>' -- uvx fetchtranscript-mcp
VS Code
code --add-mcp '{"name":"fetchtranscript","type":"stdio","command":"uvx","args":["fetchtranscript-mcp"],"env":{"FETCHTRANSCRIPT_API_KEY":"<your FETCHTRANSCRIPT_API_KEY>"}}'

Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in.

Environment variables
  • FETCHTRANSCRIPT_API_KEYrequiredsecretYour FetchTranscript API key (starts with yt_), from https://fetchtranscript.com/dashboard/api-keys

A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.

Category
Media & Creative
Version
0.2.0
Registry
active
Published
11/21/2026
Listed in:Official MCP registry ↗how this is checked

Is it safe? Is it maintained?

Serverdex check: Nov 22, 2026

Looks healthy: FetchTranscript is maintained, open source, hosted endpoint answering without a key.

Maintained
Active
Last commit today (Nov 21, 2026), 0 open issues.
Official registry
Active
Published as com.fetchtranscript/fetchtranscript in the official MCP registry, version 0.2.0.
Source
Open source, MIT
Public repository under the MIT licence, 0 stars, 0 forks.
Runs
Local package or hosted
Ships as a local package (PyPI) that runs on your machine, and as a hosted endpoint at api.fetchtranscript.com that receives what your client sends it.
Credentials
None needed to connect
The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
Owner
Unclaimed
Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.

Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.

Live check

checked Nov 22, 2026, 06:07 UTCStatus history & uptime →
● Working245 msprotocol 2025-06-18v1.30.0promptsresourcestools

The endpoint answered the MCP handshake as "FetchTranscript" and listed 8 tools. Answering since Nov 22, 2026.

Context cost ≈ 1.5k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 8 tools.

Tools (8)

  • get_transcript3 params

    Get the transcript of a YouTube video. Args: video_id: YouTube video ID (11 characters, e.g. 'dQw4w9WgXcQ') lang: Language code (e.g. 'en', 'it'). Auto-detected if omitted. format: Output format — 'text' (default), 'json' (segments with timestamps), or 'srt'.

    Show parameters
    • video_idstringrequired
    • lang
    • formatstring
  • list_languages1 param

    List available transcript languages for a YouTube video. Args: video_id: YouTube video ID (11 characters)

    Show parameters
    • video_idstringrequired
  • get_video_metadata1 param

    Get metadata for a YouTube video (title, description, views, likes, etc.). Args: video_id: YouTube video ID (11 characters)

    Show parameters
    • video_idstringrequired
  • get_chapters1 param

    Get chapter list for a YouTube video. Args: video_id: YouTube video ID (11 characters)

    Show parameters
    • video_idstringrequired
  • get_comments3 params

    Get the top-level comments of a YouTube video, each with its like and reply count. Costs 1 credit per 100 comments returned, rounded up (minimum 1): up to 100 comments cost 1 credit, 101-200 cost 2. Videos with comments turned off cost nothing. Args: video_id: YouTube video ID (11 characters) limit: Number of comments to fetch (default 20, max 500) sort: "top" (default) or "new" (newest first)

    Show parameters
    • video_idstringrequired
    • limitinteger
    • sortstring
  • get_channel_info1 param

    Get information about a YouTube channel. Args: channel_id: YouTube channel ID (UCxxxxxx format) or handle (@username)

    Show parameters
    • channel_idstringrequired
  • list_channel_videos4 params

    List videos from a YouTube channel. Args: channel_id: YouTube channel ID (UCxxxxxx format) or handle (@username) limit: Number of videos to return (default 10, max 100) offset: Number of videos to skip for pagination (default 0) include_shorts: Whether to include YouTube Shorts (default false)

    Show parameters
    • channel_idstringrequired
    • limitinteger
    • offsetinteger
    • include_shortsboolean
  • search_videos2 params

    Search YouTube videos. Args: query: Search query string limit: Number of results (default 5, max 50)

    Show parameters
    • querystringrequired
    • limitinteger

Checked by Serverdex with a plain initialize + tools/list call to api.fetchtranscript.com/mcp, no credentials, about once a day. A failed check is never a removal.

On GitHub

read Nov 22, 2026
Stars
0
Forks
0
Last push
Nov 21, 2026
License
MIT

Pythonaiclaudemcpmcp-servermodel-context-protocoltranscriptsyoutubeyoutube-transcript

From the README

FetchTranscript MCP Server 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: • 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.…

Read the full README on GitHub →

Remotes

  • streamable-httphttps://api.fetchtranscript.com/mcp

The most-starred Media & Creative servers in the index, with their live-check result.

ServerStarsLast pushLive check
HyperFrames by HeyGen87,943Nov 2026Needs sign-in
HyperFrames by HeyGen86,475Nov 2026Needs sign-in
Pascal 3D Editor25,651Nov 2026Needs sign-in
screenpipe22,421Nov 2026Local / not checked
FunASR21,097Nov 2026Local / not checked

FetchTranscript: questions people ask

Is FetchTranscript a remote or a local MCP server?
According to its entry in the official MCP registry, FetchTranscript ships as a hosted endpoint (streamable-http) that your client connects to by URL and as a local package (PyPI) that your client starts on your machine. Use the hosted endpoint when your client supports Streamable HTTP; use the package when you want it to run locally.
Does FetchTranscript need an API key?
Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
Is FetchTranscript safe to use?
Looks healthy: FetchTranscript is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: Local package or hosted; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
Is FetchTranscript still maintained?
Active: the repository's last commit today. Last push Nov 21, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 22, 2026.
What tools does FetchTranscript expose?
8 tools as listed by the server itself during the live check, including get_transcript, list_languages, get_video_metadata, get_chapters, get_comments. The full list with parameters is in the Live check section above.
How do I add FetchTranscript to Claude, Cursor or VS Code?
Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
Browse all Media & Creative →

Add the badge to your site

Show visitors that FetchTranscript is listed here — it’s also the link we check for a free listing.

FetchTranscript — listed on Serverdex

HTML — for your website

<a href="https://serverdex.io/server/com-fetchtranscript-fetchtranscript?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="FetchTranscript — listed on Serverdex" width="123" height="40" loading="lazy"></a>

Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.

Markdown — for your README

[![FetchTranscript — listed on Serverdex](https://serverdex.io/brand/badge.svg)](https://serverdex.io/server/com-fetchtranscript-fetchtranscript?utm_source=badge)

Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.

Add to CursorAdd to VS CodeOpen in Claude Code

Install buttons — for your README

[![Add to Cursor](https://serverdex.io/brand/install-cursor.svg)](https://serverdex.io/install/cursor/com-fetchtranscript-fetchtranscript) [![Add to VS Code](https://serverdex.io/brand/install-vscode.svg)](https://serverdex.io/install/vscode/com-fetchtranscript-fetchtranscript) [![Open in Claude Code](https://serverdex.io/brand/install-claude-code.svg)](https://serverdex.io/install/claude-code/com-fetchtranscript-fetchtranscript)

One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.

Install buttons — HTML for your docs

<a href="https://serverdex.io/install/cursor/com-fetchtranscript-fetchtranscript"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/com-fetchtranscript-fetchtranscript"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/com-fetchtranscript-fetchtranscript"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>

Same buttons as plain links for a docs page or website.

Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).