Skip to content
Custom Connectors

Connect Kustomer to Claude Code

Let Claude draft replies, set status, and assign conversations in Kustomer. From the terminal, inside the sessions where you already work.

How do you connect Kustomer to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Kustomer, you add a Kustomer MCP server: a small hosted service that exposes Kustomer's data and actions over the Model Context Protocol. With a custom connector we build for you, that is one command in the terminal, then an OAuth sign-in with your own Kustomer account. No API keys pasted into config files.

claude mcp add --transport http kustomer https://your-connector-url/mcp

Then run /mcp inside a Claude Code session to sign in. Add it with --scope project and the connector is checked into the repo for your whole team.

What can Claude Code do in Kustomer once connected?

A custom connector keeps that read access and adds the write actions the native tool set leaves out. Claude can draft a reply on the right conversation, set status and queue, add an internal note for the next agent, tag the conversation, and assign it to the correct person or team, all after you approve. Triage and follow-up happen where the conversation already lives.

  • Draft a reply on a conversation, preserving the customer and message history
  • Set a conversation's status to open, snoozed, or done as it moves
  • Add an internal note with context for the next agent
  • Apply tags and assign the conversation to the right team or queue
  • Update fields on a customer's timeline to keep records current
  • Search conversations matching a query and propose batched responses

One connector, every Claude surface

The connector we build is a remote MCP server, which is the same standard claude.ai and Claude Desktop use. Add it once and the same Kustomer access works in Claude Code for you, in claude.ai for the rest of the team, and in Claude Desktop. One build, one set of permissions, one monthly plan covering all of them.

Build it yourself, or have it built?

If you live in the terminal, you can absolutely write your own MCP server against the Kustomer API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Kustomer changes its API and when the MCP spec itself moves, and scoping write actions so an agent can never do more than you intended. We build Kustomer connectors with separated read and write tools and approval gates on destructive actions, then host and maintain them so they keep working while you work.

Frequently asked questions

Does the same Kustomer connector work in claude.ai and Claude Code?
Yes. It is one remote MCP server. Claude Code adds it with a single "claude mcp add" command; claude.ai and Claude Desktop add it as a custom connector in Settings. Each person signs in with their own Kustomer account, so access always matches what that person can already see and do.
Do I need to host or maintain anything myself?
No. The connector runs as a hosted service we operate: we handle uptime, token health, API changes on Kustomer's side, and MCP spec migrations under the monthly plan. Your side is one command in the terminal and an OAuth sign-in.
Is it safe to give a coding agent write access to Kustomer?
Write access is scoped, not blanket. Read tools and write tools are separated, destructive actions like deleting or sending are gated behind your explicit approval, and the connector can never exceed the permissions of the Kustomer account it signs in with. Revoking access is one click in Kustomer.

Tell us what you run. We'll build the connector.

Pick your tool, choose what Claude should do, and get an instant scope and price. No call required.