Think inside your AI world.

Intercom through Unl

Intercom can tell you a conversation is marked closed. Whether the customer's actual question got answered before it closed is a judgement call your team already made - Unl just applies it.

Intercom through Unl reads conversation and contact records against the resolution criteria you have ratified, so 'is ticket #4192 actually resolved?' comes back no, naming the reopening window it failed.

What Intercom holds

Intercom's MCP server exposes:

  • Conversation search and retrieval, including full parts, state, and assignment history
  • Contact records with custom attributes, location data and activity timestamps
  • Company records with segments, tags and custom attributes
  • Help Centre article search and full content retrieval
  • A universal search tool spanning conversations and contacts by query

What the naked read gives you

Pull conversation #4192 through Intercom's MCP server and it comes back whole: every message part, who was assigned, when it was marked closed, the contact's history and any tags attached. Search across the inbox and it returns matching conversations with state and author detail intact. It's the full record exactly as the support team left it.

The frame judges the data it is given; it does not verify the source’s accuracy.

What changes when Intercom is read measured

Tom, the Head of Support, ratified a resolution rule after a customer escalated a thread the team had already marked closed twice: a conversation only counts as resolved if the customer's original question is answered inside the thread and no follow-up message reopens it within 48 hours.

'Is ticket #4192 actually resolved?' returns, measured: no - the conversation was marked closed, but the customer sent a follow-up nine hours later that reopened it, so Tom's 48-hour condition fails. Intercom supplied the conversation state and timeline; your ratified rule supplied the reopening window that decides whether 'resolved' holds.

And back again

Close the loop with a real reply and the thread stays quiet past 48 hours, and the next check reads that straight from Intercom - no separate resolution log to update, no second system to keep in sync.

The answer comes back measured against what you already decided, and why.

The lane is live and open to this tool today: one box, paste anything. If it speaks MCP, Unl can reach it. Readings arrive unprompted, the data beside the criterion; Unl is a courier, not a warehouse, and keeps only your keys and the frame.

Questions people ask

Why would a 'closed' Intercom conversation come back as unresolved?

Because closing a conversation and answering the customer's question are two different events. Unl checks the second one against the rule your team ratified, so a thread that reopens within the window you set still fails, however the status field reads.

How do I connect Intercom to Claude?

Authorise Intercom's own MCP server, hosted at mcp.intercom.com, through OAuth from a US-hosted workspace, then link the connection inside Unl. Claude reads conversations, contacts and companies through that same authorised access.

Does Unl edit or change my Intercom conversations?

Unl reads through Intercom, and can write back on your explicit gesture — it never acts as a side effect of a read.

What this is

Think inside your AI world — you stay in command

Unlimitless (Unl to friends) holds what you've settled, reads what your tools are showing, and catches what's changed out in the world — and hands your AI whatever bears on the work, the moment it's needed, without you asking. The right thing, in front of the model, unprompted, with you in command of the call. So you keep moving toward what you set out to build, on top of everything you've already decided.

It plugs into Claude, Claude Code, ChatGPT and Cursor as an MCP connector. Quick to connect, in a couple of steps.

Unlimitless is open now to invited Alpha. Apply for the Beta waitlist to come in ahead of the full launch:

Alpha is invite-only · free at launch.