Connect GrowthBook to Claude Code
Read and toggle feature flags, and read experiments and their results, in GrowthBook. Add Toolspoke to Claude Code once and it can use 14 GrowthBook actions. Your GrowthBook credential stays in Toolspoke, and you choose which actions Claude Code may call.
Set it up in Claude Code
Three steps, the first one once for every toolkit you will ever add.
Add Toolspoke to Claude Code
Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcpThe sign-in opens in your browser, and Toolspoke asks you to approve it.
Install GrowthBook and connect it
Add GrowthBook to a project in your Toolspoke workspace.
API key. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.
- API key
- GrowthBook → your avatar → Personal Access Tokens → Create token, which acts with your own access. An admin can instead create an organization key under Settings → API Keys and give it a role, a read-only role keeps this connector to reads.
Choose what Claude Code may do
All 14 actions start on. Switch off any of the 4 actions that change something in GrowthBook, and Claude Code gets a refusal if it tries.
What you can ask Claude Code for
A few of the GrowthBook actions that only read, so they are safe to try first.
- List feature flags, optionally in one project
- List experiments, optionally narrowed to a project or a status
- Read one experiment, its hypothesis, variations, phases, metrics and status
- Read the latest analysis of one experiment, each variation's metric values and the statistics comparing them
What Claude Code can do in GrowthBook
10 actions read, 3 write and one deletes or permanently changes something.
Reads
List features
List feature flags, optionally in one project. Start here, the flag id is what every other feature action takes. It is also the install's connection test, because it needs a key that can read real data.
Get feature
Read one feature flag in full, its default value, and per environment whether it is on and which rules it serves.
List experiments
List experiments, optionally narrowed to a project or a status.
Get experiment
Read one experiment, its hypothesis, variations, phases, metrics and status.
Get experiment results
Read the latest analysis of one experiment, each variation's metric values and the statistics comparing them. Optionally for one phase or broken down by a dimension.
List projects
List the projects in this organization. A project id narrows feature and experiment lists.
List environments
List the environments in this organization, such as dev and production. Environment ids are the keys toggle_feature takes.
List metrics
List the metrics experiments can be measured by, optionally in one project.
List saved groups
List saved groups, named lists of user attributes, such as user ids or emails, that targeting rules refer to. Not written to the audit log, because the lists hold other people's identifiers.
List sdk connections
List the SDK connections, which app reads which environment and project, and with which client key.
Writes
Create feature
Create a feature flag. It serves its default value to everyone until rules are added, so a new flag changes no running app unless the default differs from what the code already assumes.
Update feature
Change a feature flag's description, owner, project, tags or default value. Fields not sent are left alone.
Toggle feature
Turn a flag on or off in one or more environments, e.g. environments {"production": true}. This changes what every SDK reading those environments serves at once. A write, not destructive, because sending the opposite value reverses it.
Deletes or permanently changes
Delete feature
Delete a feature flag in every environment. Destructive because there is no undo and SDKs still reading it get no value from then on. Prefer update_feature with archived true to retire a flag reversibly.
GrowthBook in Claude Code: questions
Does Claude Code see my GrowthBook credential?
No. The credential is stored encrypted in Toolspoke, and the gateway adds it to each call. Claude Code only ever talks to Toolspoke, and the dashboard shows the last four characters of the credential and nothing more.
Can I stop Claude Code from changing things in GrowthBook?
Yes. Each of the 14 actions can be switched off for a project. Turn off the 4 that change something and Claude Code can only read.
Will 14 actions crowd Claude Code's context?
No. Toolspoke shows Claude Code five bridge tools, plus a guide where a toolkit has one, and Claude Code searches for the GrowthBook action it needs when it needs it. Adding more toolkits does not add more tools to its list.
Can I add it once for every project?
Yes. Add --scope user to the command and Claude Code keeps Toolspoke in every project on this machine. Without it, the server is added to the project you ran the command in.
What does it cost?
Tool calls are free on every plan, and a GrowthBook call does not run in a sandbox, so it bills nothing.
GrowthBook in your other apps
Try GrowthBook in Claude Code
Free to start, and tool calls cost nothing on any plan.