intercom-mcp
Enables to search, view, and interact with Intercom contacts and conversations, including sending customer-visible replies and internal notes.
README
intercom-mcp
Dedalus MCP server for Intercom support and customer communications. It exposes contact search, contact lookup, conversation listing, conversation lookup, customer-visible replies, and internal notes.
Tools
search_contacts- Search contacts by field/operator/value or list recent contacts when no value is provided.get_contact- Fetch one contact by ID.list_conversations- List conversations, optionally filtered by state.get_conversation- Fetch one conversation by ID.reply_to_conversation- Send a customer-visible admin reply.create_note- Add an internal note to a conversation.
Safety Notes
reply_to_conversation contacts real users. Confirm the conversation, admin identity, and body before calling it. create_note is separate and documented as internal-only so agents do not accidentally send private triage notes to customers.
Intercom conversation data may contain personal data and support history. Do not commit OAuth tokens, client secrets, conversation exports, or customer messages.
Authentication
This is a Dedalus Type 4 OAuth server. The server declares one DAuth connection named intercom-mcp with secret key INTERCOM_ACCESS_TOKEN. Dedalus handles OAuth authorization, token exchange, and runtime credential injection.
Deployment variables:
OAUTH_ENABLED=true
OAUTH_AUTHORIZE_URL=https://app.intercom.com/oauth
OAUTH_TOKEN_URL=https://api.intercom.io/auth/eagle/token
OAUTH_CLIENT_ID=...
OAUTH_CLIENT_SECRET=...
OAUTH_SCOPES_AVAILABLE=read_admins,read_contacts,write_contacts,read_conversations,write_conversations
OAUTH_BASE_URL=https://api.intercom.io
INTERCOM_VERSION=2.14
DEDALUS_AS_URL=https://as.dedaluslabs.ai
Adjust scopes to the minimum needed for your Intercom app and workspace approval flow.
Run Locally
uv run python src/main.py
In another terminal:
MCP_SERVER_URL=http://127.0.0.1:8080/mcp uv run python src/_client.py
src/_client.py explicitly calls every tool. Use INTERCOM_TEST_CONTACT_ID, INTERCOM_TEST_CONVERSATION_ID, and INTERCOM_TEST_ADMIN_ID to point the smoke test at safe records.
Deploy
Publish as dedalus-labs/intercom-mcp, configure OAuth in Dedalus, deploy, then run:
DEDALUS_MCP_SERVER_ONLY=1 DEDALUS_MCP_SERVER=dedalus-labs/intercom-mcp uv run python src/_client.py
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。