The Statsig MCP Server lets AI agents manage feature flags, create and analyze A/B experiments, inspect dynamic configs and metrics, query logs, and review audit history within Statsig projects.
The fastmcp library is a Python client for MCP servers. Use it to call MewCP tools from your own scripts and services.
This guide connects Statsig MCP to Python through MewCP, so Python can use Statsig MCP's 10 tools, like get_context, search and fetch, without your Statsig MCP credentials ever reaching the app.
Statsig MCP signs in through managed OAuth. MewCP stores the token encrypted, refreshes it before it expires and injects it only at call time. Your agent never holds it, so it can never leak it.
More apps
Manage repositories, pull requests, issues, branches and development workflows on GitHub. Automate software delivery and collaborate across engineering projects.
Connect to external APIs, webhooks and internet services through standard HTTP requests. Build integrations with virtually any platform that exposes a web-based interface.
Full Google Search Console control for search analytics, sitemaps, sites, and URL inspection, directly from your AI workflows. This MCP server exposes the Google Search Console API for querying search traffic data, managing sitemaps and site properties, and inspecting the indexing status of any URL. It is built for SEO teams monitoring search performance, developers automating sitemap and property management, and analysts pulling search traffic data into reporting pipelines.
Give AI coding agents access to a curated library of real-world website designs, screenshots, design systems, and reusable UI components. Search visual references, find similar designs, analyze layouts, extract colors and typography, compare websites, and retrieve copy-ready JSX components for building better interfaces
Other clients
Statsig MCP works the same way in every client below. Pick yours for its own guide.
Free to start.
Scope access to the exact Statsig MCP tools and accounts you allow, work and personal side by side. Anything outside that scope is refused at call time, even when the model asks for it.
Each call is logged: what ran, on which account, and whether it worked. Failures come back structured, so the agent knows whether to retry instead of guessing.
Every app sits behind one secure MCP URL, and there is no server for you to deploy or keep running. Add an integration in the dashboard and it is live on the next call, with no config to change and no new credentials to wire up. Tools load only when a task needs them, so your agent stays fast and focused however many apps you connect.
SDK clients sign in with an API key. Create one in your dashboard and replace API_KEY in the code below.
SDK clients run without a browser, so they sign in with your API key.
Get bounded project, permission, review, and product context.
Search Statsig resources across supported product areas after the user identifies a resource type or target. For an underspecified request such as asking about “the rollout” without naming a gate or config, ask a clarifying question before searching.
Fetch a resource selected from a search result.
List, get, and inspect feature gates and their history.
List, get, inspect, and retrieve experiment results.
List, get, and inspect dynamic configs and their history.
List and inspect metrics and metric sources.
Query Logs Explorer and inspect project audit and change history.
Find a long-tail API operation. Start with action=resolve, a plain-language query, operationAction when known, and category when the request clearly names one resource type. Use resolve_many for independent steps in a chained request. Omit uncertain filters, especially lane: updates and review approval or commit commonly use api_destructive. A resolved result names the exact execution tool and handle. Use list only for ambiguity, then get the selected operation.
Execute a discovered read-only public API operation.
