Transcript MCP server
Give Claude, Cursor, Windsurf or your own agent tools to search YouTube, list TikTok profiles and read video transcripts. Remote server with OAuth sign in, or run it with npx.
Updated
The MCP server gives an AI agent the same API as your key: it can find videos, transcribe them and read the results in the middle of a conversation. It charges your credits. Nothing to install: point the client at the remote server, https://www.transcriptdock.com/mcp.
Connect#
Claude (claude.ai, Desktop, mobile)#
- Open Customize, Connectors and choose Add custom connector.
- Name it Transcript Dock and paste
https://www.transcriptdock.com/mcpas the server URL. Leave the advanced settings empty. - Choose Add, then Connect. Sign in to Transcript Dock and choose Allow access.
No API key is involved: the connector signs in with your account and can read and submit jobs and read transcripts, never keys, billing or account settings. On Team and Enterprise plans an Owner adds it once under Organization settings, Connectors, and each member connects.
ChatGPT#
- In ChatGPT on the web, open Plugins, select + and choose Add custom MCP server.
- Name it Transcript Dock, paste
https://www.transcriptdock.com/mcpas the server URL and choose OAuth as the authentication. - Save it, sign in to Transcript Dock and choose Allow access.
Custom MCP servers are available on ChatGPT plans that allow them, such as Business, Enterprise and Edu, and a workspace admin can switch them off. Like the Claude connector, it signs in with your account and never sees keys or billing.
Claude Code#
Add the server, then run /mcp in Claude Code and choose Authenticate to sign in.
claude mcp add --transport http transcriptdock https://www.transcriptdock.com/mcp
For CI and scripts, send an API key instead of signing in:
claude mcp add --transport http transcriptdock https://www.transcriptdock.com/mcp \--header "Authorization: Bearer td_live_YOUR_KEY"
Cursor and other clients#
{"mcpServers": {"transcriptdock": {"url": "https://www.transcriptdock.com/mcp","headers": { "Authorization": "Bearer td_live_YOUR_KEY" }}}}
Windsurf uses serverUrl instead of url, and VS Code lists servers under servers with "type": "http". The client pages below have the exact files.
- Claude CodeOne terminal command.
- Claude appclaude.ai, Desktop and mobile: add a custom connector.
- CursorAdd to mcp.json.
- WindsurfAdd to mcp_config.json.
- OpenClawAutonomous agents over stdio.
Local server#
For stdio only clients such as OpenClaw, run the same server locally with Node.js 22.15 or newer. Both variables are required.
{"mcpServers": {"transcriptdock": {"command": "npx","args": ["-y", "@transcriptdock/mcp"],"env": {"TRANSCRIPTDOCK_API_KEY": "td_live_YOUR_KEY","TRANSCRIPTDOCK_BASE_URL": "https://www.transcriptdock.com"}}}}
wait_for_job again.Tools#
| Tool | Does | Credits |
|---|---|---|
get_video_transcript | URL in, transcript out. Submits, waits, returns text (or srt, vtt, segments). | 1, or 2 per minute with AI transcription |
transcribe | Submit a job and return it without waiting. | Same |
wait_for_job | Wait for a job to finish. | Free |
get_job | Job status, error and billing. | Free |
get_transcript | Read a transcript by id as segments, text, srt or vtt. | Free |
list_jobs | Recent jobs. | Free |
search_youtube | Search YouTube. | 1 per page |
list_channel_videos | A channel's videos, newest first, with paging. | 1 per page |
get_channel_latest_videos | A channel's latest 10 videos. | 1 |
search_channel_videos | Search inside one channel. | 1 per page |
list_playlist_videos | A playlist's videos. | 1 per page |
list_tiktok_user_videos | A TikTok profile's latest videos (up to 10) and profile stats. | 1 |
get_video_discovery | Read a discovery by id, e.g. after a timeout. | Free |
get_video_transcript#
The tool an agent should reach for when asked what a video says.
{ "url": "https://www.youtube.com/watch?v=dQw4w9WgXcQ" }
Never gonna give you upNever gonna let you down…
The same video with the same mode is answered from your workspace's stored result, free.
transcribe, wait_for_job, get_transcript#
The three-step version for agents that want control: transcribe takes url, mode, optional language and max_credits, plus an idempotency_key (any stable 8 to 128 character string, so a retried call never submits twice) and returns the job. wait_for_job takes job_id and an optional timeout_seconds. get_transcript takes the job's result_id as transcript_id and a format.
Finding videos#
The search and list tools return videos with url, title, duration and view count, ready to pass to get_video_transcript. channel accepts an @handle, channel id or channel URL; playlist an id or URL; user a TikTok @user or profile URL. YouTube tools page with limit (default 20) and cursor. TikTok returns at most 10 videos and no further pages; include_details adds likes, comments, hashtags and caption languages per video.
Errors#
A failed call returns isError: true with the API error code, message and request id, so the agent can explain it or change course. The codes are the ones in the API reference.
Troubleshooting#
- Unauthorized: in Claude, remove the connector and add it again to sign in fresh. With a key, it goes in the server config (header or env), not in your shell; check it has not been revoked.
- Couldn't reach the MCP server: use the exact URL
https://www.transcriptdock.com/mcp, including www. - Tool not found: restart the client after editing its config.
- Local server will not start: install Node.js 22.15 or newer and set both
TRANSCRIPTDOCK_API_KEYandTRANSCRIPTDOCK_BASE_URL. - NO_CAPTIONS: the video has no captions. On a paid plan, ask for
mode: "auto".