home / mcp / zoom transcript mcp server
An MCP server for interacting with Zoom Cloud Recording transcripts
Configuration
View docs{
"mcpServers": {
"forayconsulting-zoom_transcript_mcp": {
"command": "node",
"args": [
"/path/to/zoom-transcripts-server/build/index.js"
],
"env": {
"ZOOM_CLIENT_ID": "your_zoom_client_id",
"TRANSCRIPTS_DIR": "/path/to/transcripts/directory",
"ZOOM_ACCOUNT_ID": "your_zoom_account_id",
"ZOOM_CLIENT_SECRET": "your_zoom_client_secret"
}
}
}
}This MCP server provides a structured interface to interact with Zoom Cloud Recording transcripts, letting you list meetings, download transcripts, fetch recent transcripts, and search across downloaded transcripts with organized, month-based storage.
You use an MCP client to connect to this Zoom Transcript MCP Server. From there you can list Zoom meetings that have recordings, download transcripts for specific meetings, pull transcripts from recent meetings, and search through all downloaded transcripts for keywords. Transcripts are stored in a clear folder structure by month, and each transcript has accompanying metadata that helps you understand its origin and contents.
Prerequisites you need before installing: Node.js version 16 or higher.
Step 1: Clone the project and enter the directory.
git clone https://github.com/yourusername/zoom_transcript_mcp.git
cd zoom_transcript_mcpStep 2: Install dependencies.
npm installStep 3: Build the project.
npm run buildStep 4: Run the server locally using the built index. You can start it with the standard Node invocation for the built output.
node build/index.jsStep 5: Create a configuration file or environment file to provide Zoom credentials and the transcripts directory path as shown below.
Create a .env file in the root directory with the following variables.
ZOOM_ACCOUNT_ID=your_zoom_account_id
ZOOM_CLIENT_ID=your_zoom_client_id
ZOOM_CLIENT_SECRET=your_zoom_client_secret
TRANSCRIPTS_DIR=/path/to/transcripts/directory # Optional, defaults to ./transcriptsAlternatively, configure the MCP server through your MCP settings file using this exact structure.
{
"mcpServers": {
"zoom-transcripts": {
"command": "node",
"args": ["/path/to/zoom-transcripts-server/build/index.js"],
"env": {
"ZOOM_ACCOUNT_ID": "your_zoom_account_id",
"ZOOM_CLIENT_ID": "your_zoom_client_id",
"ZOOM_CLIENT_SECRET": "your_zoom_client_secret",
"TRANSCRIPTS_DIR": "/path/to/transcripts/directory" // Optional
}
}
}
}To obtain credentials, sign in to Zoom App Marketplace and create a Server-to-Server OAuth app. Note your Account ID, Client ID, and Client Secret after configuring the required scopes.
Transcripts are saved under a year-month folder with individual transcript files named by date, time, topic, and meeting ID. Metadata files accompany each transcript containing details like topic, start time, duration, and participants.
You can build and run locally using the standard project commands, and you should provide the Zoom credentials and transcripts directory in the environment to enable transcript access and storage.
MIT
Lists available Zoom meetings that have cloud recordings, with optional date ranges or participant filters.
Downloads a transcript for a specific meeting by ID or UUID.
Downloads transcripts from the most recent meetings, up to a specified count.
Searches across downloaded transcripts for a given query and optional date range.