Connect LaunchDarkly to Claude Code

Let Claude toggle flags and update targeting in LaunchDarkly. From the terminal, inside the sessions where you already work.

Build my connector Talk to us

How do you connect LaunchDarkly to Claude Code?

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

claude mcp add --transport http launchdarkly 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 LaunchDarkly once connected?

Full read-write LaunchDarkly access lets Claude toggle a flag in a specific environment, update targeting rules and percentage rollouts, add or remove flags from segments, and adjust a flag's default variation, once you approve. The flag changes that meant clicking through the dashboard happen where the request was made.

Toggle a feature flag on or off in a specified environment
Update targeting rules or percentage rollout for a flag
Add or remove users and segments from a flag's targeting
Change a flag's default variation or fallthrough behavior
Create a new feature flag with variations from a description
Archive or remove a stale flag after you confirm

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

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

More on the LaunchDarkly connector

LaunchDarkly connector for claude.ai Bitbucket + Claude Code CircleCI + Claude Code Jenkins + 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