Integrations · Helpdesk

Automate Intercom work with your agents

Maplith maps how Intercom’s conversations, contacts (users and leads), companies, and tickets join your payments, web shop, CRM and spreadsheets, so your agent knows where each thing is and how far to trust each join.

Maplith’s Intercom integration is built and rolling out. Until it reaches your workspace, connect Intercom to your own agent today; Maplith maps it from there.

WayStatusWhat it means
Your own agentAvailableIntercom connector in Claude (US-hosted workspaces) or Intercom synced app in ChatGPT, read-only.
Export filesAvailableCSV exports: the last three months.
Maplith reads Intercom itselfRolling outBuilt, and not open to every workspace yet.
Example flows

What your agents do with Intercom and Maplith

What starts the work, what your agent does with Maplith, and how it ends. Each flow uses the Intercom data and joins described below.

01

A new conversation nobody has picked up

Trigger: A customer opens a conversation in Intercom, and no teammate is assigned to it.

With Maplith:

  1. Signals: With Maplith’s Intercom integration (rolling out), the conversation arrives as a support_case_opened signal. Until it reaches your workspace, your agent looks for new conversations in Intercom with its own read access.
  2. Task context: get_task_context on the case returns the playbook “Work a new Intercom support case”, if you put it in use, and what the agent’s key may do.
  3. Route: route from the conversation to its contact by contact id, then to the same person in your shop or billing system by email or by the external user id.
  4. The action gate: request_action for a task for whoever assigns the inbox: the case, the customer found in your shop or billing system, and the team the playbook names. A person assigns it in Intercom.
  5. Record and value: record_action records who took the case and how it ended.

Result: Whoever assigns the inbox gets the case with the customer already found in your other systems.

02

A ticket that carries an order number

Trigger: A customer raises a ticket about a delivery, and the order number sits in one of the ticket’s attributes.

With Maplith:

  1. The map: get_object on the tickets says whether your ticket type keeps an order number in an attribute, and which one.
  2. Route: route from the ticket to the order in your shop by that order number, with how far Maplith trusts the hop.
  3. Findings: Where a scan found tickets whose order number matches no order, a finding says so, with its evidence and a recommendation.
  4. The action gate: The agent drafts a reply from the order’s fulfillment status, which it read in the shop with its own access, and request_action decides whether a person approves the reply. Maplith never sends it: your agent does, only with write access you give it in Intercom separately (its Write conversations permission), once approved.
  5. Record and value: record_action records the reply and closes the loop on the ticket.

Result: The customer gets the delivery status from the order, not a request to repeat the order number.

03

The same person as a lead and a user

Trigger: Billing asks which Intercom contact belongs to a paying customer, and finds a lead and a user with the same email.

With Maplith:

  1. Ask: ask: “how do Intercom’s contacts tie to our billing customers?” The answer cites its joins: by email, or by the external user id your product sends.
  2. Route: route from the Intercom contact to the Stripe customer by email, with how much Maplith trusts that hop.
  3. The map: get_object on the contacts says which of the two carries the external user id; the agent reads both contacts in Intercom with its own read access.
  4. The action gate: request_action for a task for the person who looks after Intercom’s contacts, with both contacts and the id that should decide between them.
  5. Record and value: record_action records the task and which contact was kept.

Result: Billing and support talk about the same person, keyed by the id your product sends.

Steps that use request_action or record_action need an agent key that may act; a read-only key reads the map.

Access

How it connects

Through access you already have. Until Maplith’s Intercom integration reaches your workspace, Maplith holds no Intercom credential and never writes there.

  1. Connect your assistant to Maplith over MCP, by signing in or with an agent key.
  2. Your agent reads Intercom with the Intercom connector in Claude (US-hosted workspaces) or the Intercom synced app in ChatGPT, read-only.
  3. With your approval it sends what it read; Maplith builds the map and deletes the files again.
When Maplith’s Intercom integration reaches your workspace
  1. In Maplith, open Data sources › Systems and choose Connect Intercom, or click Install on Maplith in Intercom's App Store. You need to be an admin or builder of the workspace.
  2. Intercom asks you to approve read access to the workspace: sign in to Intercom as a teammate who may install apps, and approve it there.
  3. Intercom returns you to Data sources › Systems. Maplith checks that it is you, in the workspace you started from, before it stores anything; the access token is sealed and never shown again.
  4. Scan it from the connection, or wait for the workspace's scan schedule.

What Maplith’s Intercom integration never reads or does

  • Anything that changes Intercom: the server's tools that write an article or an internal note are never called.
  • Tickets, articles, news items, data exports or settings: the permissions for them are not asked for.
  • Your access token anywhere but sealed in Maplith: it is never shown again and never sent to a model.
  • A US- or AU-hosted workspace: only Intercom's EU server is read, so those workspaces share an export or let their own agent read Intercom.

The permissions it asks for, and why

PermissionWhy
Read conversationsReads the conversations the support process and the support playbooks are built from: their state, times, assignee and tags
Read and list users and companiesLists the contacts and companies a conversation belongs to, so a case can be joined to the same person or company in the shop or the billing system
Read one user and one companyReads one contact or company when a conversation names it

What Maplith never reads or does

  • Intercom itself: until Maplith’s Intercom integration reaches your workspace, Maplith holds no Intercom credential and never signs in to it.
  • Anything that changes Intercom: Maplith never writes there. When your agent acts, it uses access you gave it.
  • What you leave out: you decide what your agent shares or an export contains.

Datasets that make a good map

Conversations

One customer conversation in the inbox, with its state, timestamps, assignee and tags.

  • conversation id
  • contact id
  • company id
  • assigned teammate id
  • team id
  • tags
  • created at
  • closed at

Contacts (users and leads)

One person the company talks to: a signed-up user or an anonymous lead.

  • contact id
  • external user id
  • email (Maplith tries to mask it)
  • company id
  • signed up at
  • last seen at

Companies

One customer company, with the id the company gives it and its custom attributes.

  • company id
  • company name
  • user count
  • created at
  • custom attributes

Tickets

One ticket of a given ticket type, raised by a customer or the team.

  • ticket id
  • ticket type
  • contact id
  • linked conversation id
  • state
  • created at

Teammates and tags

One support teammate or team, and the tags used to sort conversations.

  • admin id
  • team id
  • tag id
  • tag name

The narrowest access Intercom offers for reading

  • Read conversations
  • Read and list users and companies
  • Read one user and one company
  • Read tickets
  • Read tags
  • Read admins

A workspace admin, or a teammate with the permissions "Can access Developer Hub" and "Can install, configure and delete apps".

Checked against Intercom’s documentation on 19 October 2026. Sources and export steps: Read Intercom into Maplith.

FAQ

Questions about Intercom and Maplith

Does Maplith copy my Intercom data?
No. Maplith keeps metadata about your data: which datasets Intercom holds, their fields, and how they join your other systems. It does not keep copies of the records. What your agent shares is read for a build and then deleted. The map may quote example values and evidence.
Which Intercom access does Maplith need?
Through your own agent, none: Maplith holds no Intercom credential for it. If your agent connects to Intercom’s MCP server directly, a private app with only read permissions, or a teammate’s own sign-in, gives it access; its token goes into the client your agent connects with, never into a chat. When Maplith’s Intercom integration reads Intercom, it asks only for: Read conversations, Read and list users and companies and Read one user and one company. Maplith keeps that access sealed, never shown again and never sent to a model.
Which AI assistants work with Maplith and Intercom?
Any assistant that speaks MCP, such as Claude, ChatGPT or one you build, connects to Maplith by signing in or with an agent key. To read Intercom, it uses the Intercom connector in Claude (US-hosted workspaces) or the Intercom synced app in ChatGPT, read-only. It reads the map, then does the work in Intercom with its own access. Connect your own agent
Where is my Intercom data processed?
In the EU, except model inference. Hosting, database and file storage are in the EU. Model inference runs in the United States under standard contractual clauses: to build the map, samples of the files and, in the findings step, whole files are sent to Maplith’s model provider, which deletes them within 30 days. Security states the details.
Does Maplith change anything in Intercom?
No. Maplith’s Intercom integration never changes anything in Intercom: the server's tools that write an article or an internal note are never called. When your agent acts in Intercom, it uses access you gave it. If its key may act, it can ask Maplith first whether the action may go ahead under your key’s policy, and Maplith keeps the log.
What about customer emails and other personal data in Intercom?
Intercom’s contacts hold emails, and its conversations hold what people write. Maplith tries to mask email local parts, the phone number a helpdesk export declares on a contact, and the names in an export’s own name columns (on by default; an admin can switch it off). It is a best-effort safeguard, not a guarantee, and it does not cover a name that appears only in the message text: leave out what must not be processed.
How does Maplith read Intercom itself?
Conversations, contacts and companies, through the six read-only tools of Intercom's MCP server, as Intercom API pages the build reads and deletes with the run. Who is on a conversation as an id, its tags, and the message text the support process is described from; Maplith tries to mask personal data in it as it does in an uploaded export. What reaches the map: the helpdesk's objects, the conversation process (opened, assigned, first reply, closed) and a playbook for each kind of case. Maplith reads everything the read tools list, whatever its age, up to a bounded amount; there is no filter to set. To read less, share an export instead of connecting. Only mcp.eu.intercom.com is read. It is built, and opens to every workspace once it is released. Until then, connect Intercom to your own agent today; Maplith maps it from there.
Which Intercom data makes a good map?
Conversations, contacts (users and leads), companies, tickets and teammates and tags. For a first map, the exports cover the last three months.

Map Intercom with the rest of your business