Intercom MCP Server

What does “Intercom” MCP Server do?

The Intercom MCP (Model Context Protocol) Server is an MCP-compliant tool that allows AI assistants to access and analyze customer support data from Intercom. Acting as a bridge between AI agents and Intercom’s API, this server enables tasks such as searching conversations and tickets with advanced filters (by customer, status, date, keywords, etc.), as well as searching email content even when no contact exists. Efficient server-side filtering is performed via Intercom’s search API, streamlining the retrieval of relevant support information. By integrating with MCP-compliant AI assistants, the Intercom MCP Server enhances development workflows for customer support automation, analytics, and more.

List of Prompts

List of Resources

List of Tools

Use Cases of this MCP Server

• Customer Support Ticket Search: Developers can enable AI assistants to retrieve and filter Intercom conversations or tickets, improving agent productivity by surfacing relevant support cases quickly.
• Advanced Filtering for Analytics: AI tools can use the server to analyze support activities by status, customer, keyword, or date range, facilitating customer satisfaction analysis and trend monitoring.
• Email Content Search: Supports searching for conversations by email content even when a contact is not present, offering a more comprehensive view of support history.
• Seamless AI Integration: Integrates easily with MCP-compliant AI tools, enabling automation and workflow enhancements for support teams.
• Server-side Filtering and Efficiency: By leveraging Intercom’s own search API, developers benefit from fast, efficient, and scalable data retrieval for downstream AI or reporting tasks.

How to set it up

Windsurf

1. Install Node.js (v18.0.0+).
2. Obtain your Intercom API token from your Intercom account settings.
3. Edit your Windsurf configuration file to add the Intercom MCP server.
4. Add the MCP server entry with a JSON snippet as shown below.
5. Restart Windsurf and verify by checking the MCP server status endpoint.

"mcpServers": {
  "intercom-mcp": {
    "command": "npx",
    "args": ["@raoulbia-ai/mcp-server-for-intercom@latest"],
    "env": {
      "INTERCOM_ACCESS_TOKEN": "${INTERCOM_ACCESS_TOKEN}"
    }
  }
}

Note: Store your Intercom API key securely as an environment variable.

Claude

1. Ensure Node.js is installed.
2. Get your Intercom API token.
3. Locate Claude’s MCP configuration section.
4. Add the Intercom MCP server using the JSON below.
5. Restart Claude and confirm the MCP server is active.

"mcpServers": {
  "intercom-mcp": {
    "command": "npx",
    "args": ["@raoulbia-ai/mcp-server-for-intercom@latest"],
    "env": {
      "INTERCOM_ACCESS_TOKEN": "${INTERCOM_ACCESS_TOKEN}"
    }
  }
}

Cursor

1. Install Node.js (v18+).
2. Acquire Intercom API token.
3. Open Cursor’s configuration file for MCP servers.
4. Insert the configuration snippet below.
5. Restart Cursor and validate the setup.

"mcpServers": {
  "intercom-mcp": {
    "command": "npx",
    "args": ["@raoulbia-ai/mcp-server-for-intercom@latest"],
    "env": {
      "INTERCOM_ACCESS_TOKEN": "${INTERCOM_ACCESS_TOKEN}"
    }
  }
}

Cline

1. Install Node.js (18+).
2. Get your Intercom API token.
3. Edit Cline’s MCP server configuration.
4. Add the Intercom MCP entry with the snippet below.
5. Restart Cline and check the server endpoint for confirmation.

"mcpServers": {
  "intercom-mcp": {
    "command": "npx",
    "args": ["@raoulbia-ai/mcp-server-for-intercom@latest"],
    "env": {
      "INTERCOM_ACCESS_TOKEN": "${INTERCOM_ACCESS_TOKEN}"
    }
  }
}

Tip: Always secure API keys by referencing them via environment variables as shown.

Example with env and inputs

"mcpServers": {
  "intercom-mcp": {
    "command": "npx",
    "args": ["@raoulbia-ai/mcp-server-for-intercom@latest"],
    "env": {
      "INTERCOM_ACCESS_TOKEN": "${INTERCOM_ACCESS_TOKEN}"
    },
    "inputs": {
      "INTERCOM_ACCESS_TOKEN": "string"
    }
  }
}

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "intercom-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “intercom-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Based on the available information, the Intercom MCP Server is a focused, practical server for Intercom integration, but lacks detailed MCP feature documentation and tool/resource listings. The documentation is solid for setup but incomplete on advanced MCP features.

Our opinion

This MCP server provides a valuable bridge between AI tools and Intercom but does not document the full range of MCP primitives such as prompts, tools, and resources. It’s well-scoped for Intercom support use cases but scores lower on MCP completeness and transparency.

MCP Score