What is Grain Mcp Server

Grain MCP Server is a Model Context Protocol server designed for Grain, a service that records and transcribes meetings. It allows users to access Grain functionalities without needing an enterprise API or paid integrations.

Use cases

Use cases include retrieving a list of recent meetings, downloading transcripts for record-keeping, and integrating meeting data into other applications without requiring paid services.

How to use

To use the Grain MCP Server, add its configuration to your MCP client. You need to specify the command, arguments, and the absolute path for browser session data. After the initial setup, you can log in to Grain via the browser.

Key features

Key features include tools for retrieving all meetings and downloading meeting transcripts in various formats (vtt or srt). It automates browser interactions using Playwright.

Where to use

Grain MCP Server can be used in various fields such as business, education, and any organization that conducts meetings and requires transcription services.

Grain MCP Server

A Model Context Protocol server for Grain, a service that records and transcribes meetings.

This server provides integration with Grain through MCP, allowing users to access Grain functionality without needing the enterprise API (which is only available on enterprise subscriptions) or paid integrations like Zapier. The service is based on Playwright for browser automation.

Installation

Manual Installation

Add the Grain MCP server configuration to your MCP client:

{
  "mcpServers": {
    "grain_uvx": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/eadm/grain-mcp-server",
        "grain-mcp-server",
        "--user-data-dir",
        "<absolute-path-to-browser-session-data>"
      ]
    }
  }
}

Replace <absolute-path-to-browser-session-data> with the absolute path where you want to store the browser session data. On first MCP usage, you will need to login to Grain via the browser.

Components

Tools

1. get_all_meetings: Retrieve all meetings from Grain

   • Returns a list of dictionaries containing meeting information, including:
     • id (string): Meeting ID
     • title (string): Meeting title
     • url (string): URL to access the meeting
     • date (string): Meeting date in ISO format

2. download_meeting_transcript: Download a meeting transcript

   • Required inputs:
     • absolute_save_path (string): The file path where the transcript will be saved
     • meeting_id (string): The unique identifier of the meeting
     • transcription_type (string): The format of the transcript file (“vtt” or “srt”)
   • Returns:
     • bool: True if the download was successful, False otherwise

Usage Examples

Some example prompts you can use with your MCP client to interact with Grain:

1. “Show me all my recent meetings” → execute the get_all_meetings tool to retrieve a list of all meetings stored in Grain

2. “Download the transcript for my last team meeting” → use get_all_meetings to find the meeting, then use download_meeting_transcript to download its transcript

Development

1. Install dependencies:

uv sync

2. Run the application:

uv run grain-mcp-server

3. Run with debug mode:

uv run grain-mcp-server --debug

4. Run tests:

uv run pytest