The GrowthBook MCP server allows interaction with GrowthBook from an LLM client, enabling users to view experiment details and manage feature flags.
From the registry: MCP Server for interacting with GrowthBook
Please install the `growthbook-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **GrowthBook API key** — Get a GrowthBook API key or Personal Access Token (https://docs.growthbook.io/integrations/mcp)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@growthbook/growthbook-mcp"]
- required environment variables:
- `GB_API_KEY`: GrowthBook API key or PAT (example: `<your-growthbook-api-key>`)
- `GB_EMAIL`: Your email address used with GrowthBook (example: `<your-email>`)
- optional environment variables:
- `GB_API_URL`: GrowthBook API URL (example: `https://api.growthbook.io`)
- `GB_APP_ORIGIN`: GrowthBook app URL (example: `https://app.growthbook.io`)
Note: README only documents env vars; full setup per client is in the official docs at docs.growthbook.io/integrations/mcp. Npx invocation inferred from package name.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.GB_API_KEYrequiredA GrowthBook API key or PAT. When using a PAT, MCP server capabilities are limited by its permissions.GB_EMAILrequiredYour email address used with GrowthBook. Used when creating feature flags and experiments.Real-time infrastructure monitoring with metrics, logs, alerts, and ML-based anomaly detection.
Validate oh-my-posh configurations and segment snippets against the official schema.
Real-time Kubernetes network traffic visibility and API analysis for HTTP, gRPC, Redis, Kafka, DNS.