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
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.