Connect Segment to Claude Code

Let Claude send events and update traits in Segment. From the terminal, inside the sessions where you already work.

How do you connect Segment to Claude Code?

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

claude mcp add --transport http segment 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 Segment once connected?

Full read-write Segment access lets Claude send track and identify calls, update user and account traits, create or edit sources and destinations, and adjust event filters once you approve. The data plumbing that used to mean hand-built scripts or console clicks happens where your customer data already flows.

Send a track or identify call to record an event or update a profile
Update user or account traits in a Segment space
Create a new source and copy its write key for an app
Enable, disable, or reconfigure a destination from a source
Add or edit an event filter to drop or transform incoming data
Look up a profile by user id and propose trait corrections

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 Segment 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 Segment API. The protocol is open. What you take on is everything around the happy path: OAuth token refresh, hosting, monitoring, keeping up when Segment 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 Segment 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 Segment 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 Segment 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 Segment'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 Segment?

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

More on the Segment connector

Segment connector for claude.ai Braze + Claude Code Iterable + Claude Code Customer.io + 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