Ingest Intercom into Graphlit

Connect Intercom to Graphlit so tickets, conversations, contacts, and help articles become searchable support context, then let agents create or update ticket workflows.

Ingest + deliver

1 ingest surface • 1 delivery surface

Intercom OAuth

Connected account boundary

Graphlit API

createFeed + queryContents

MCP-native

Agent context and delivery flows

Ingest

What gets ingested

Graphlit reads the selected Intercom surfaces, converts the source material into searchable content, and keeps enough source metadata for grounded answers, retrieval, and downstream agent workflows.

Intercom tickets and conversations

Feed type: Issue / IntercomTickets

IntercomTickets
Tickets and ticket parts
Conversations and replies
Help-center articles
Contacts and ticket state

Setup fields

Ticket StateInclude Internal NotesInclude AttachmentsItem Limit

Deliver

Deliver through Intercom

Delivery pages show the full path from context to action: Graphlit retrieves context from Intercom, agents reason over that context, and approved outputs are delivered through MCP tools and connected accounts.

Create or update Intercom ticket

Delivery path: Graphlit MCP + Intercom

create, replace, comment
Create tickets from retrieved support context
Update ticket state and ticket parts
Add comments to existing tickets
Resolve contact and assignee names

Prepare

What Graphlit prepares

The integration is not just a connector. Graphlit turns Intercom into content that can be searched, cited, summarized, enriched with observations, and supplied to agents through the Graphlit API and MCP.

{
  "source": "Intercom",
  "content": "Intercom tickets and conversations",
  "extracted": [
    "entities",
    "observations",
    "facts",
    "summaries"
  ],
  "citations": [
    "Intercom source references"
  ],
  "agentContext": {
    "searchable": true,
    "groundedAnswers": true,
    "deliveryEnabled": true
  }
}

Use cases

What you can build with Intercom

01

Build a Intercom knowledge base from tickets and ticket parts and conversations and replies and search it alongside the rest of your Graphlit content.

02

Ask grounded questions over Intercom context without forcing users to leave the tools where the work originally happened.

03

Extract people, organizations, projects, events, facts, and decisions from Intercom content so agents can reason over durable context.

04

Let approved agents create tickets from retrieved support context after retrieving the source context that justifies the delivery.

Need a code sample? Ask our AI assistant

SDK:
Try:or

FAQ

Common questions

Start building

Start building with Intercom and Graphlit

Create a free Graphlit project, connect Intercom, and turn real operational context into retrieval, knowledge graphs, and MCP-native agent workflows.

Create free account