GrowthBook is an open-source A/B testing and feature flagging platform that helps teams run experiments and manage feature rollouts. It provides SDKs, APIs, and visual interfaces for experimentation and analytics.
13 of 33 checks passed. 14 unscored.
Can an agent find and understand this tool without a web search?
Can an agent create an account and get credentials without human intervention?
Can an agent operate autonomously without upfront payment or contracts?
How well does the API work for non-human consumers?
Does the tool fail gracefully when an agent makes a mistake?
GrowthBook has good documentation and a published OpenAPI spec, making discovery reasonably straightforward. The API uses simple API key authentication and supports programmatic experiment creation and evaluation. However, account creation requires manual signup with email verification, limiting autonomous agent onboarding. The SDKs are solid but MCP integration is absent. Reliability appears moderate with standard rate limiting, and the free tier is generous for experimentation but lacks formal SLA guarantees.
Install the Agent Native Registry MCP server. Your agents can search, compare, and score tools mid-task.
claude mcp add --transport http agent-native-registry https://agentnativeregistry.com/api/mcp