Intercom MCP Server
Enables AI agents to manage Intercom support workflows, including searching and updating contacts, handling conversations, assigning and closing tickets, and logging notes.
README
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
| Tool | What it does |
|---|---|
search_contacts |
Find a contact by email, name, or phone |
create_or_update_contact |
Create a new contact or update an existing one |
search_conversations |
Filter conversations by status, contact, or assignee |
reply_to_conversation |
Send a customer reply or internal note |
close_conversation |
Resolve and close an open conversation |
assign_conversation |
Route a conversation to an admin or team |
create_contact_note |
Add an internal audit note to a contact's profile |
Quickstart
1. Get your Intercom API token
- Go to app.intercom.com
- Navigate to Settings → Developer Hub → Your App → Authentication
- 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
- Push this repo to GitHub (private repo is fine)
- Create a new project at railway.app
- Connect your GitHub repo — Railway auto-detects Node.js
- Add environment variable:
INTERCOM_API_TOKEN = your_token - Deploy — Railway gives you a public URL
Environment Variables
| Variable | Required | Description |
|---|---|---|
INTERCOM_API_TOKEN |
Yes | Your Intercom Bearer token |
Requirements
- Node.js 18 or higher
- An Intercom account (free developer workspace works for testing)
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。