Turn recurring Intercom support themes into Linear issues

Customer support · Dev, web & IT · checked 2026-10-18

Claude reads last week's Intercom conversations through Intercom's MCP server, groups repeated product problems and drafts Linear issues. A person reviews them before anything is filed.

Independent review. IonBin has no partnership with any tool on this page and was not paid for this page. Our evaluation is our own, based on public documentation and our research. Product names are trademarks of their owners and are used for identification only. How disclosure works.

Goal

Get repeated customer problems in front of the product team as a short list of reviewed issues.

Connects through: MCP

Steps

  1. Intercom

    Returns last week's closed conversations through the search and search_conversations tools on Intercom's MCP server

    MCPConfirmedSource ↗

  2. Claude

    Groups conversations by product problem and drafts one issue per theme, with conversation links and a count

    AI platformConfirmed

  3. You

    Remove anything personal, merge duplicates and approve the drafts

    Human stepConfirmed

  4. Linear

    Creates the approved issues in the right team through Linear's MCP server

    MCPConfirmedSource ↗

Confirmed means the vendor documents it (linked). It doesn't mean IonBin has tested it. AI-platform and human steps need no source.

Human approval

Nothing is filed in Linear until you approve each draft.

Watch out for

Conversation text can include personal data, so keep it out of issue descriptions and link to the conversation instead. Grouping by theme is a judgment call, so check that each draft really matches its conversations. To browse before you approve, connect Linear's read-only endpoint, and switch to the full endpoint only when you file.

Starter prompt

Using the Intercom MCP server, find conversations closed in the last 7 days. Group them by product problem and only keep themes that show up in at least 3 conversations. For each theme, draft a Linear issue with a one-line title, a short description in plain words, the conversation count and links to the conversations. Leave out customer names, email addresses and any other personal details. Show me the drafts and wait for my approval before creating anything in Linear.

Written for this workflow. Paste it into your AI platform and adjust it to your situation.

Tools in this workflow

ToolRoleOfficial site
IntercomMCP intercom.com ↗
LinearMCP linear.app ↗
ClaudeAI platform claude.ai ↗

Which AI platforms can run it

PlatformStatusWhy
Claude (incl. Claude Code) To verify Intercom: MCP pairing needs route-specific evidence; a named plugin or CLI does not establish it; Linear: MCP pairing needs route-specific evidence; a named plugin or CLI does not establish it
OpenAI Codex To verify Intercom: MCP pairing needs route-specific evidence; a named plugin or CLI does not establish it; Linear: MCP pairing needs route-specific evidence; a named plugin or CLI does not establish it
Google Antigravity To verify Intercom: MCP pairing needs route-specific evidence; a named plugin or CLI does not establish it; Linear: MCP pairing needs route-specific evidence; a named plugin or CLI does not establish it
ChatGPT To verify Intercom: MCP pairing needs route-specific evidence; a named plugin or CLI does not establish it; Linear: MCP pairing needs route-specific evidence; a named plugin or CLI does not establish it
Gemini To verify Intercom: MCP pairing needs route-specific evidence; a named plugin or CLI does not establish it; Linear: MCP pairing needs route-specific evidence; a named plugin or CLI does not establish it
Perplexity To verify Intercom: MCP pairing needs route-specific evidence; a named plugin or CLI does not establish it; Linear: MCP pairing needs route-specific evidence; a named plugin or CLI does not establish it

Readiness considers the connection evidence and unresolved steps. Confirmed: documented access and the proposed steps meet the recorded requirements. MCP and API pairings require an explicit reviewed platform note; a named plugin or CLI alone does not confirm MCP. Inferred: an explicit page note describes a plausible pairing that still needs testing. To verify: a connection or step is unresolved. An API and code execution alone do not establish compatible network access, credentials or permissions. None of this is IonBin testing.

What we checked (2026-10-18)

  • Intercom MCP server. Intercom documents a remote server for US-hosted workspaces at https://mcp.intercom.com/mcp and for EU-hosted ones at https://mcp.eu.intercom.com/mcp. It offers 14 tools, including a universal search for conversations and contacts and a search_conversations tool with filters for state, assignee and timing. Requests to the EU endpoint are processed in the EU.
  • Linear MCP server. Linear hosts its server at https://mcp.linear.app/mcp, with OAuth 2.1 or an API key. A read-only endpoint at /mcp/readonly is available for lookups.

Set it up

  1. Use the Intercom endpoint for your region. The workspace URL tells you which one: app.intercom.com is US and app.eu.intercom.com is EU.
  2. Connect Linear. Use the read-only endpoint while you review, and the full endpoint only to file approved issues.
  3. Once a week, run the prompt above and read every draft against its linked conversations.
  4. Strip personal details, merge duplicates of existing Linear issues, then approve the drafts you want filed.

This is a proposed sequence based on documented tools, not a tested account integration.

OpenAI’s Linear skill has the same read-first habit: it reads issues before changing them and explains bulk changes before applying them. IonBin reviewed it from source only.

Sources

No affiliate links on this page. No paid placements in workflows. How IonBin makes money.