Intercom MCP Server
Connect to the Intercom MCP server to search conversations, manage contacts, handle tickets, and read help center articles using AI agents on Gumloop, Claude, or Cursor.
Try Intercom now
Type what you want done. Sign in and run it live with an AI agent.
|
Intercom
Installation
Get StartedCreate a Gumloop Account
To use this MCP, you need a Gumloop account. If you don't have one yet, you can create one for free.
Copy Your Server URL
Copy your MCP server URL and add it to your client. You'll be prompted to authorize on first use.
Tools (23)
Search Contacts
Search for contacts in Intercom using various criteria with advanced filtering capabilities. If no search parameters are provided, lists all contacts.
Update Contact
Update or manage a contact
Create Contact
Create a new contact in Intercom
Create Conversation
Create a new conversation in Intercom by sending the first message
Reply To Conversation
Reply to an existing conversation in Intercom. By default, replies as an admin. Only specify user_id if you want to reply on behalf of a specific contact/user.
Update Conversation
Manage conversation tags and contacts
Search Conversations
Search for conversations in Intercom using various criteria with advanced filtering capabilities. If no search parameters are provided, lists all conversations.
Retrieve Conversation
Retrieve a single conversation with all its details and conversation parts
Search Companies
Search for companies in Intercom using various criteria. If no search parameters are provided, lists all companies using the scroll API.
Create Company
Create a new company in Intercom
Associate Contact With Company
Associate a contact with a company
List Articles
List articles
What is Intercom MCP?
The Intercom MCP server gives AI agents access to your Intercom customer messaging and support data. That means agents can search conversations and tickets, read full conversation threads, reply to customers, create and update contacts and companies, open and triage tickets, apply tags, and pull help center articles for reference. It works across the core Intercom support workflow: conversations, contacts, companies, tickets, and articles.
If your team spends time digging through the Intercom inbox for context, copying conversation details into spreadsheets, manually triaging tickets, or assembling support reports by hand, an AI agent can take over much of that busywork. Describe what you need, and your AI agent will handle the support operations for you.
MCP stands for Model Context Protocol. It’s an open standard that gives AI agents a way to connect to external tools and services. Instead of registering an Intercom OAuth app, handling the authorization flow, and writing code against the Intercom API to manage pagination and rate limits, you connect your Intercom account to Gumloop once. After that, you manage your support pipeline just by chatting with your AI agent.
Related MCP servers
Zendesk MCP Server
Interact with Zendesk tickets, views, and support features
Freshdesk MCP Server
Interact with Freshdesk to read, triage, and respond to support tickets, manage contacts and companies, work with the knowledge base, and orchestrate community forums.
HubSpot MCP Server
Interact with HubSpot CRM for managing contacts, companies, and deals
Salesforce MCP Server
Interact with Salesforce data and execute operations
Slack MCP Server
Interact with Slack channels and messages
Gmail MCP Server
Interact with Gmail emails and messages
What you can do with Intercom MCP on Gumloop
Search conversations and read full threads
Search conversations by contact, admin, team, state, date, tags, or priority, then retrieve any single conversation with all of its parts. Retrieval supports a plaintext mode that strips HTML, so an AI agent can summarize a long thread or pull out the key context without you scrolling the inbox.
Reply to customers and start new conversations
Reply to an existing conversation as an admin or on behalf of a user, or create a brand-new conversation that sends a first message to a contact. Your AI agent can draft and send responses, follow up on stalled threads, or kick off proactive outreach.
Create and triage support tickets
Search tickets by state, assignee, type, title, description, or date, and pull full details on any ticket. Agents can create tickets, update fields, change state, reassign, snooze, and add comments, so routine triage and follow-up happen without manual clicking.
Manage contacts
Find contacts by name, email, phone, role, tag, or domain, create new contacts as users or leads, and update existing ones. Updates cover editing details, applying or removing tags, and archiving or blocking a contact when needed.
Work with companies
Search companies by name, ID, tag, or segment, retrieve a single company, and list every contact that belongs to it. Agents can also create companies and associate a contact with a company to keep account records connected.
Pull help center articles
List help center articles, optionally filtered by collection, and retrieve any article by ID. Your AI agent can reference existing support content when answering questions or drafting replies. Article access is read-only.
Apply and read tags
List every workspace tag, then apply or remove tags on contacts, conversations, and tickets. This keeps records organized and makes later searches more precise.
Look up workspace context
Identify the authenticated admin and list the workspace’s ticket types so an agent has the reference data it needs to assign, categorize, and route work correctly.
How to connect the Gumloop Intercom MCP Server
- 1
Create a free Gumloop account
Sign up at gumloop.com. No credit card required.
- 2
Add the Intercom MCP server
Copy your MCP server URL from Gumloop and add it to your preferred client (Claude, Cursor, or Gumloop workflows). You'll authorize on first use.
- 3
Start using Intercom in your AI workflows
That's it. Your AI agent can now search conversations, reply to customers, triage tickets, manage contacts and companies, and pull help center articles across your Intercom workspace. Use it inside a Gumloop automation, in Claude Desktop, or in Cursor.
Intercom MCP use cases
Faster inbox triage for support teams
When new conversations land, a Gumloop agent can search the open inbox, retrieve each thread in plaintext, summarize the issue, apply the right tags, and reply with a first response or tag it for the right team. Support reps spend their time resolving issues instead of reading and sorting.
Ticket follow-up for support managers
An AI agent can search tickets by state and assignee, surface anything stalled or overdue, add a status comment, snooze or reassign where needed, and compile a daily summary into Slack or Google Sheets. Managers see the queue clearly without exporting reports by hand.
Customer context for success teams
Pull a contact and their company, list the other contacts at that account, and retrieve recent conversations to build a quick account snapshot before a call. Your AI agent can hand a customer success manager the full picture (open issues, recent replies, tags) in seconds.
Knowledge-grounded replies for CX ops
An agent can list and retrieve help center articles, match the right one to a customer’s question, and draft a reply that cites existing support content. This keeps answers consistent with your documented guidance and reduces back-and-forth.
Cross-platform support agents
Connect Intercom with Slack, Gmail, Google Sheets, and other MCP tools in a single agent. Post new high-priority conversations to a Slack channel, sync ticket data to a reporting sheet, or email a customer when their ticket changes state, so Intercom talks to the rest of your stack automatically.
Why use Gumloop for Intercom MCP
Connect once, no tokens to manage
Many Intercom MCP servers you’ll find on GitHub make you register your own OAuth app, handle the authorization flow, and store credentials in environment variables. With Gumloop you authorize your Intercom account once and stay connected. There are no client secrets or token files to manage, and no need to code against the Intercom API.
Works with multiple MCP clients
Use the Intercom MCP server endpoint in Claude Desktop, Cursor, or directly inside Gumloop agents. Same server URL, works with any MCP client.
Chain Intercom with 100+ other integrations
Combine Intercom with Slack, Gmail, Google Sheets, HubSpot, and other MCP tools in a single AI agent. Pull a conversation from Intercom, process it with an LLM, and write the result to a ticket, a sheet, or another tool.
Enterprise-grade and scalable
Built for teams, with role-based permissions and dedicated support for Pro users. The server respects your existing Intercom access controls, so an agent only reaches what your connected account can. For details on Gumloop’s security practices, see trust.gumloop.com.
Pricing includes a free plan
You can test the Intercom MCP integration on Gumloop’s free tier before committing. Paid plans start at $37/month.
Frequently asked questions
Ship Intercom agents in minutes
Connect any AI agent to 100+ MCP servers, zero setup.