Intercom MCP server

The MCP Intercom Server provides access to Intercom conversations and chats through Model Context Protocol. This server enables LLMs to query and analyze your Intercom conversations with various filtering options, helping you gain insights from customer communications.

Features

• Query Intercom conversations with filtering options:
  • Date range (start and end dates)
  • Customer ID
  • Conversation state
• Secure access using your Intercom API key
• Rich conversation data including:
  • Basic conversation details
  • Contact information
  • Statistics (responses, reopens)
  • State and priority information

Installation

Prerequisites

• Node.js
• npm
• Intercom API key

Setup Steps

1. Clone the repository:

   git clone https://github.com/fabian1710/mcp-intercom.git
   cd mcp-intercom
   

2. Install dependencies:

   npm install
   

3. Set up your environment:

   cp .env.example .env
   

4. Add your Intercom API key to .env:

   INTERCOM_API_KEY=your_api_key_here
   

5. Build the server:

   npm run build
   

Usage

Running the Server

Start the server with this simple command:

npm start

Integrating with Claude for Desktop

1. Add the server to your Claude for Desktop configuration file:

   On macOS:

   ~/Library/Application Support/Claude/claude_desktop_config.json
   

   On Windows:

   %AppData%\Claude\claude_desktop_config.json
   

2. Add the following configuration:

   {
     "mcpServers": {
       "intercom": {
         "command": "node",
         "args": ["/path/to/mcp-intercom/dist/index.js"],
         "env": {
           "INTERCOM_API_KEY": "your_api_key_here"
         }
       }
     }
   }
   

3. Restart Claude for Desktop to apply the changes

Using the search-conversations Tool

The server provides a powerful tool to search Intercom conversations with various filters.

Parameters

• createdAt (optional): Object with operator (e.g., ">", "<", "=") and value (UNIX timestamp)
• updatedAt (optional): Object with operator (e.g., ">", "<", "=") and value (UNIX timestamp)
• sourceType (optional): Source type (e.g., "email", "chat")
• state (optional): Conversation state (e.g., "open", "closed")
• open (optional): Boolean to filter by open status
• read (optional): Boolean to filter by read status

Example Queries

You can ask Claude to perform queries like:

• "Search for all conversations created after January 1, 2024"
• "Find conversations updated before last week"
• "List all open email conversations"
• "Get all unread conversations"

Security Considerations

• Your Intercom API key should be kept secure
• The server provides read-only access to conversations
• All API requests use proper authentication
• Consider using environment variables rather than hardcoding your API key

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.