Integration
Connect Intercom to Anthropic
When New company fires in Intercom, your agent runs Anthropic agent message in Anthropic. Describe the whole flow and it is built, tested on every scenario and kept running.
What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.
Build solutions, not workarounds.
What do you want Intercom and Anthropic to do together?
Ask the assistant
Connect your AI client
Give your AI client this address.
https://mcp.apiant.aiOne connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.
Set it up in your client
Claude Code
Run this in the directory you want to work in.
claude mcp add --transport http -s project apiant-ai https://mcp.apiant.aiStart Claude Code there, approve the server, and sign in in the browser page it opens.
Claude Code guide (opens in a new tab)Claude, web and desktop
Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.
Setup guide (opens in a new tab)Cursor
Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.
Setup guide (opens in a new tab)Zed
Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.
Setup guide (opens in a new tab)Codex and the ChatGPT desktop app
Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.
Setup guide (opens in a new tab)Any other MCP client
Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.
Setup guide (opens in a new tab)Intercom holds your conversations, tickets and contact records; Anthropic runs Claude models that can read that text and write something back. Joining them lets a new Intercom conversation or ticket go to Claude for a summary, a category or a draft reply, and lets the result land back on the Intercom record as a note, an assignment or a message.
Example flows
What Intercom can start in Anthropic
When New company in Intercom
then Anthropic agent message in Anthropic
Starting points drawn from the triggers and actions in the catalog today. Describe the flow you need, at any depth, and your agent builds it and tests every scenario before it ships.
Everything your agent can do with Intercom and Anthropic
Triggers and actions 4 triggers · 33 actions
- New company
Fires when a new company is created.
- New conversation
Polls for conversations, most recently updated first. Fires for each new conversation.
- New or updated contact
Polls for contacts, most recently updated first. Fires for each new or updated contact.
- New ticket
Fires when a new ticket is created.
- Add note to contact
Adds a note to the specified contact as the specified admin.
- Add note to conversation
Adds an internal note to the specified conversation as an admin.
- Add tag to contact
Attaches a tag to the specified contact.
- Assign conversation
Assigns the conversation to an admin or team.
- Close conversation
Closes the specified conversation.
- Create message
Creates an admin-initiated email or in-app message to a contact.
- Delete company
Delete a company by ID.
- Delete contact
Deletes a contact by ID.
- Find admin by email
Fetches an admin's details. Lists all admins; match by email.
- Find contact by email
Searches contacts by email and returns matches.
- Find tickets
Search tickets by criteria.
- Get company
Retrieve a company by ID.
- Get contact
Fetches a contact's details by ID.
- Get conversation
Fetches a conversation's details by ID.
- Get ticket
Retrieve a ticket by ID.
- List companies
List all companies.
- List segments
List all segments.
- List tags
Lists all tags for the workspace.
- Open conversation
Opens (marks open) the specified conversation.
- Remove tag from contact
Detaches a tag from the specified contact.
- Send conversation reply
Sends a reply to the specified conversation as an admin.
- Snooze conversation
Snoozes the specified conversation until the given unix timestamp.
- Start conversation
Starts a new conversation with the specified contact.
- Track event
Submit a data event for a contact.
- Anthropic agent message
Runs one AI agent turn on Anthropic and returns the model's reply. The turn is billed to the Anthropic account connected on this step, and the agent can call the account's AI tool automations.
- Cancel message batch
Cancel a Message Batch that is still processing.
- Count tokens in a message
Count the number of input tokens a Messages API request would use, without creating the message.
- Create message batch
Submit a batch of Messages API requests for asynchronous processing.
- Get message batch
Retrieve the status and request counts of a Message Batch by id.
- Get model
Retrieve details for a specific Claude model by id.
- List message batches
List Message Batches in the workspace, most recently created first.
- List models
List the available Claude models, most recently released first.
- Send model a message
Send a message to a Claude model and return its response. Supports the full Messages API: model, system prompt, multi-turn messages, max_tokens, tools, and adaptive thinking.
No trigger or action matches that. Ask your agent to add it: it reads the API documentation and builds what you describe.
Each app on its own
Reviews
What our customers say
More from Intercom
Intercom to HubSpotHubSpot is your all-in-one stop for all of your marketing software needs.
Intercom to SalesforceSalesforce is a leading enterprise customer relationship management (CRM) platform.
Intercom to SlackSlack is a messaging platform for teams. Post messages, manage channels, users, reminders, and react to...
Intercom to StripeStripe is a payment processing platform for online businesses.
Intercom to QuickBooks OnlineQuickBooks Online accounting — manage customers, invoices, bills, payments, vendors, expenses, and more via...
Intercom to PipedrivePipedrive is a sales CRM and pipeline management tool.
More into Anthropic
Mailchimp to AnthropicMailchimp marketing automation and email platform.
Shopify to AnthropicShopify is a commerce platform for online stores and retail point-of-sale.
Questions
Intercom and Anthropic, answered
Can Claude reply to a customer in Intercom directly?
Yes, an Intercom conversation reply or message can be sent with wording that Claude returned from Anthropic. Many teams prefer to place it as an internal note on the conversation first so an admin reads it before anything reaches the customer.
What starts a run, since Anthropic has no triggers?
Every run starts in Intercom, for example a new conversation, a new ticket, a new or updated contact, a new company or a note added to a conversation. Anthropic is used on the action side, to send a model a message, run an agent turn, count tokens or submit a message batch.
What can start an automation from Intercom?
Any of Intercom's 4 triggers in the catalog, including New company, New conversation, New or updated contact and New ticket. Describe the moment in plain language and your agent picks the right one.
What can your agent do in Anthropic when something happens in Intercom?
Any of Anthropic's 9 actions, including Anthropic agent message, Count tokens in a message, Create message batch and Send model a message. Your agent maps the data both ways and tests every scenario before it ships.
Can it also run from Anthropic to Intercom?
Anthropic has no triggers in the catalog today, so automations start in Intercom. If you need the other direction, ask: your agent reads Anthropic's API documentation and adds it.
Do I have to build a connector for Intercom or Anthropic?
No. Both are in the catalog with their triggers and actions. You describe the automation; your agent builds it, tests every scenario and keeps it running.
Can my AI client use Intercom and Anthropic without building an automation?
Yes. With your AI client connected to APIANT, ask it to do something in either app once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running. One connection covers both.
What happens when something fails?
Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.
Is there a free plan?
Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.