mcp-transkriptor
Allows transcription of files from Dropbox via public URL.
Allows transcription of files from Google Drive via public URL.
Allows transcription of live Google Meet meetings.
Allows transcription of YouTube videos via URL.
Allows transcription of live Zoom meetings.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-transkriptorTranscribe my latest meeting recording"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-transkriptor
Local MCP server wrapping the Transkriptor developer API. Transcribe audio, video, public URLs (YouTube / Google Drive / Dropbox / OneDrive), and live meetings (Google Meet / Microsoft Teams / Zoom); fetch transcription content and AI summaries; export TXT / SRT / PDF / DOCX; manage files, folders, custom vocabulary and webhooks; text-to-speech; and AI-chat knowledgebases. stdio transport.
Requirements
A Transkriptor API key — see https://developer.transkriptor.com (authentication)
Related MCP server: Deepgram MCP Server
Setup
git clone https://github.com/mickaelxd/mcp-transkriptor.git
cd mcp-transkriptor
cp .env.example .env # then paste your TRANSKRIPTOR_API_KEY
uv syncRun / test
uv run mcp-transkriptor # starts the stdio server (Ctrl-C to stop)Register in Claude Code
claude mcp add transkriptor -s user -- \
uv run --directory /absolute/path/to/mcp-transkriptor mcp-transkriptorUse the absolute path to your clone. Other MCP clients: point them at the same
uv run --directory <path> mcp-transkriptor command over stdio.
Configuration
Env var | Required | Purpose |
| yes | Sent as |
| no | Sandbox for |
Tools
Transcribe:
transcribe_local_file,transcribe_url,transcribe_meetingRead:
get_file_content,get_file_detail,get_meeting_detail,get_summary,list_files,list_folders,get_user_detailsExport / edit:
export_transcription,rename_file,delete_fileVocabulary:
set_custom_vocabulary,get_custom_vocabulary,delete_custom_vocabularyWebhooks:
create_webhook,list_webhooks,delete_webhookText-to-speech:
text_to_speechAI chat:
list_knowledgebases,create_knowledgebase,add_file_to_knowledgebase,create_chat_session,chat_with_knowledgebase
Base URL https://api.tor.app/developer, rate limit 1000 req/min. Everything keys
off the order_id returned by a transcribe call.
Security
Your API key grants full account access.
.envis gitignored — keep it that way. Treat the key like a password and rotate it if it leaks.This server exposes destructive tools (
delete_file,delete_webhook, andset_custom_vocabulary, which replaces existing vocabulary). If you run your MCP client without a tool-confirmation gate, an autonomous agent — or indirect prompt injection via transcription content the model reads — could trigger them. Prefer a client that confirms tool calls.transcribe_local_fileuploads file contents to a third party (tor.app). KeepTRANSKRIPTOR_ALLOWED_DIRnarrow; never point it at a directory holding secrets.get_user_detailsechoes account fields returned by the API; avoid pasting its raw output into shared logs.Webhooks require a public HTTP endpoint to receive events. This server can create / list / delete them, but does not host a receiver.
License
MIT — see LICENSE.
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/mickaelxd/mcp-transkriptor'
If you have feedback or need assistance with the MCP directory API, please join our Discord server