Intercom Mcp Server

Created By
ShackletonAnalytics17 days ago
MCP server for Intercom. Give AI agents native access to contacts, conversations, replies, assignments, and ticket resolution. Covers the 7 core Intercom API actions that handle 80% of agent workflows.
Overview

Intercom MCP Server

A hosted MCP server that gives AI agents full access to Intercom's core support workflows-search contacts, manage conversations, reply, assign, close tickets, and log notes.

Built on the Model Context Protocol using the official @modelcontextprotocol/sdk.


Tools

ToolWhat it does
search_contactsFind a contact by email, name, or phone
create_or_update_contactCreate a new contact or update an existing one
search_conversationsFilter conversations by status, contact, or assignee
reply_to_conversationSend a customer reply or internal note
close_conversationResolve and close an open conversation
assign_conversationRoute a conversation to an admin or team
create_contact_noteAdd an internal audit note to a contact's profile

Quickstart

1. Get your Intercom API token

  1. Go to app.intercom.com
  2. Navigate to Settings → Developer Hub → Your App → Authentication
  3. Copy your Access Token

For testing, create a free developer workspace at app.intercom.com/developers — no paid plan required.


2. Clone and install

git clone https://github.com/your-username/intercom-mcp-server.git
cd intercom-mcp-server
npm install

3. Set your environment variable

cp .env.example .env

Open .env and add your token:

INTERCOM_API_TOKEN=your_token_here

4. Connect to Claude Desktop

Add this to your Claude Desktop config file:

Mac: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "intercom": {
      "command": "node",
      "args": ["/absolute/path/to/intercom-mcp-server/index.js"],
      "env": {
        "INTERCOM_API_TOKEN": "your_token_here"
      }
    }
  }
}

Restart Claude Desktop. You should see the Intercom tools available.


5. Test with the MCP Inspector

npx @modelcontextprotocol/inspector node index.js

This opens a browser UI at http://localhost:5173 where you can call each tool manually and inspect responses.


Deployment on Railway

  1. Push this repo to GitHub (private repo is fine)
  2. Create a new project at railway.app
  3. Connect your GitHub repo — Railway auto-detects Node.js
  4. Add environment variable: INTERCOM_API_TOKEN = your_token
  5. Deploy — Railway gives you a public URL

Environment Variables

VariableRequiredDescription
INTERCOM_API_TOKENYesYour Intercom Bearer token

Requirements

  • Node.js 18 or higher
  • An Intercom account (free developer workspace works for testing)

License

MIT

Server Config

{
  "mcpServers": {
    "intercom": {
      "command": "node",
      "args": [
        "/absolute/path/to/intercom-mcp-server/index.js"
      ],
      "env": {
        "INTERCOM_API_TOKEN": "your_intercom_api_token_here"
      }
    }
  }
}
Project Info
Created At
17 days ago
Updated At
15 days ago
Author Name
ShackletonAnalytics
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Tavily Mcp
@tavily-ai

JavaScript
a year ago