Gong MCP server

The Gong MCP Server implements the Model Context Protocol to give Claude access to Gong's API for retrieving call recordings and transcripts. This server bridges Claude with your Gong data, allowing you to query information about calls and access detailed conversation transcripts.

Prerequisites

• Node.js 18 or higher
• Docker (optional, for containerized deployment)
• Gong API credentials (Access Key and Secret)

Installation

Local Setup

Install and build the server locally:

npm install
npm run build

Docker Setup

Build a Docker container for the server:

docker build -t gong-mcp .

Configuration

Setting Up Claude with the MCP Server

1. Open Claude Desktop settings
2. Navigate to the MCP Servers section
3. Add a new server with the following configuration:

{
  "command": "docker",
  "args": [
    "run",
    "-it",
    "--rm",
    "gong-mcp"
  ],
  "env": {
    "GONG_ACCESS_KEY": "your_access_key_here",
    "GONG_ACCESS_SECRET": "your_access_secret_here"
  }
}

Make sure to replace the placeholder credentials with your actual Gong API credentials.

Using the MCP Server

The Gong MCP Server provides two main tools:

List Calls

This tool retrieves a list of Gong calls with optional date range filtering.

Input Schema:

{
  "type": "object",
  "properties": {
    "fromDateTime": {
      "type": "string",
      "description": "Start date/time in ISO format (e.g. 2024-03-01T00:00:00Z)"
    },
    "toDateTime": {
      "type": "string",
      "description": "End date/time in ISO format (e.g. 2024-03-31T23:59:59Z)"
    }
  }
}

The response includes call details such as ID, title, start/end times, participants, and duration.

Retrieve Transcripts

This tool retrieves detailed transcripts for specified call IDs.

Input Schema:

{
  "type": "object",
  "properties": {
    "callIds": {
      "type": "array",
      "items": { "type": "string" },
      "description": "Array of Gong call IDs to retrieve transcripts for"
    }
  },
  "required": ["callIds"]
}

The response includes detailed transcripts with speaker IDs, topics, and timestamped sentences.

Example Workflow

1. Use the list_calls tool to find calls within a specific date range
2. Note the call IDs from the results
3. Use the retrieve_transcripts tool with those IDs to get the detailed conversation transcripts
4. Analyze the transcripts or have Claude interpret the conversations

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.