Skip to main content
Glama
Social Media Video Transcripts

Social Media Video Transcripts

Official
README.md
<p align="center">
  <img src="https://raw.githubusercontent.com/TranscriptFetch/youtube-tiktok-instagram-transcript-mcp/main/assets/logo.png" alt="TranscriptFetch" width="84" height="84" />
</p>

# TranscriptFetch MCP Server

A [Model Context Protocol](https://modelcontextprotocol.io) server that gives any MCP client (Claude Desktop, Cursor, and others) access to the [TranscriptFetch API](https://transcriptfetch.com/?utm_source=github&utm_medium=mcp&utm_campaign=youtube-tiktok-instagram-transcript-mcp): a production transcript API for YouTube, TikTok and Instagram, with AI transcription when captions are missing. Fetch transcripts, search videos, list channels and playlists, and check your credit balance.

## Get an API key

1. Create a free account at [transcriptfetch.com](https://transcriptfetch.com/sign-up?utm_source=github&utm_medium=mcp&utm_campaign=youtube-tiktok-instagram-transcript-mcp). No card needed.
2. Open [Dashboard, then API keys](https://transcriptfetch.com/app/keys?utm_source=github&utm_medium=mcp&utm_campaign=youtube-tiktok-instagram-transcript-mcp) and create a key. It starts with `tf_live_`.
3. Put it in `TRANSCRIPTFETCH_API_KEY` in the client configuration below.

Every account gets 50 free credits a month. Failures are free: a fetch that returns no transcript is never charged.

Runs locally over stdio and calls the TranscriptFetch API with your key. Prefer a hosted, remote server? Point your client at `https://transcriptfetch.com/mcp` instead (OAuth or API key). The hosted server waits inline for short-form AI transcription, so no polling is needed there.

## Tools

| Tool | What it does |
|---|---|
| `get_transcript` | Transcript for a video: YouTube, TikTok, Instagram, or a direct media URL. When a video has no captions but has speech, the audio is transcribed automatically; `ai_fallback: true` goes straight to the audio. Optional `markdown` (timestamped, linked paragraphs), `chunks` (about 500 tokens each, for a vector store) and `timestamps: false` for text only |
| `search_videos` | Search YouTube (default), TikTok or Instagram. On YouTube, filter by `upload_date`, `duration` and `captions`, and `sort` by views |
| `search_channels` | Find YouTube channels (default) or playlists by keyword |
| `list_channel_videos` | A YouTube channel's videos, Shorts or live streams (`tab`), sorted newest, popular or oldest, or searched with `query`; also a TikTok or Instagram profile |
| `list_channel_playlists` | A YouTube channel's playlists, or its podcasts |
| `list_playlist_videos` | A YouTube or TikTok playlist's videos |
| `get_credits` | Remaining credit balance for the key. Never billed |

These are the same seven tools, with the same inputs, as the hosted server at `https://transcriptfetch.com/mcp`: `npm run sync-tools` regenerates them from its public card.

Pricing is per successful result: a caption fetch or a video list costs 1 credit, and AI transcription of the audio costs 1 credit per started 5 minutes of audio, charged only on delivery. Failed, blocked and empty results are never charged, which matters on short-form video where many clips have no speech at all.

## Install

No install needed. Run it on demand with `npx`:

```bash
TRANSCRIPTFETCH_API_KEY=tf_live_... npx -y transcriptfetch-mcp
```

Or install globally:

```bash
npm install -g transcriptfetch-mcp
```

Requires Node 18+.

### Run from source

```bash
git clone https://github.com/TranscriptFetch/mcp-server
cd mcp-server && npm install && npm run build
```

Then point your client at the built entrypoint with `"command": "node"` and
`"args": ["/absolute/path/to/mcp-server/dist/index.js"]`.

## Client configuration

### Claude Desktop

Add this to `claude_desktop_config.json` (Settings then Developer then Edit Config):

```json
{
  "mcpServers": {
    "transcriptfetch": {
      "command": "npx",
      "args": ["-y", "transcriptfetch-mcp"],
      "env": { "TRANSCRIPTFETCH_API_KEY": "tf_live_..." }
    }
  }
}
```

### Cursor

Add the same block under `mcpServers` in your Cursor MCP settings.

Restart the client, and the five tools appear.

## Example

Once connected, ask your assistant naturally:

> Get the transcript for https://youtu.be/aircAruvnKk and summarize the key points.

> Search YouTube for "how transformers work" and list the top 5 videos.

> List the latest videos from @lexfridman and pull the transcript of the newest one.

> How many TranscriptFetch credits do I have left?

The assistant picks the matching tool and works from the returned transcript or video list.

## Configuration

| Env var | Required | Default |
|---|---|---|
| `TRANSCRIPTFETCH_API_KEY` | yes | none |
| `TRANSCRIPTFETCH_BASE_URL` | no | `https://transcriptfetch.com` |

## Docker

The server speaks MCP over stdio, so there is no port to expose. `-i` is
required: without an attached stdin the transport closes immediately and the
container looks like it crashed.

```bash
docker build -t transcriptfetch-mcp .
docker run --rm -i -e TRANSCRIPTFETCH_API_KEY=tf_live_... transcriptfetch-mcp
```

## Links

- API docs: https://transcriptfetch.com/docs?utm_source=github&utm_medium=mcp&utm_campaign=youtube-tiktok-instagram-transcript-mcp
- MCP docs: https://transcriptfetch.com/docs/mcp?utm_source=github&utm_medium=mcp&utm_campaign=youtube-tiktok-instagram-transcript-mcp
- Node SDK: https://github.com/TranscriptFetch/transcript-api-node
- Python SDK: https://github.com/TranscriptFetch/transcript-api-python

## License

MIT

TDQS

A4.1/5.0

Scored across 5 tools

Disambiguation5/5

Each tool targets a distinct resource: credit balance, channel video listing, playlist video listing, search results, and transcript fetching. The three discovery tools (search_videos, list_channel_videos, list_playlist_videos) are cleanly separated by their input source, so an agent can easily pick the right one.

Naming Consistency5/5

All five tools follow a consistent verb_noun snake_case pattern (get_credits, list_channel_videos, list_playlist_videos, search_videos, get_transcript). No deviations or mixed conventions.

Tool Count5/5

Five tools is well-scoped for a transcript-fetching service, covering discovery, retrieval, and account status without redundancy. Every tool earns its place.

Completeness4/5

Core workflow (discover videos via search/channel/playlist, then fetch transcript) is fully covered, plus a credits check and a documented AI-fallback path. Minor gap: no dedicated video-details/metadata tool, though get_transcript partially compensates by accepting IDs/URLs.

Maintenance

ActivityMaintained
ResponsivenessNo recent community issues