Connect Crisp to Claude Code

Let Claude draft replies, triage, and resolve conversations in Crisp. From the terminal, inside the sessions where you already work.

Build my connector Talk to us

How do you connect Crisp to Claude Code?

Claude Code reaches outside tools through MCP servers. To connect Crisp, you add a Crisp MCP server: a small hosted service that exposes Crisp'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 Crisp account. No API keys pasted into config files.

claude mcp add --transport http crisp 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 Crisp once connected?

Full read-write Crisp access lets Claude reply inside the original conversation, keep the contact and channel intact, apply segments, set the conversation state, assign an operator, and add private notes. The triage and drafting that used to mean switching tabs happen where the conversation already lives, once you approve.

Draft a reply inside an existing conversation, preserving the contact and channel
Add or remove segments to triage and route incoming conversations
Assign a conversation to a specific operator
Set a conversation to resolved, pending, or unresolved as you clear the queue
Add a private note for the next operator without messaging the contact
Find every conversation 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 Crisp 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 Crisp API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Crisp 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 Crisp 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 Crisp 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 Crisp 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 Crisp'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 Crisp?

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 Crisp account it signs in with. Revoking access is one click in Crisp.

More on the Crisp connector

Crisp connector for claude.ai Gorgias + Claude Code Kustomer + Claude Code Zoho Desk + Claude Code

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.

Build my connector Talk to us