MCP server · Developer tools · official
ConfigCat MCP server
by configcat · official
Lets your AI look up and manage your ConfigCat feature flags, configs, environments and products for you.
This is a small helper that connects your AI assistant to ConfigCat, the service many teams use to switch features on and off without releasing new code. Once it is set up, you can ask your AI in plain words to find a feature flag, change its value, or create a new one. It is handy for developers, product people and anyone who works with feature flags but does not want to click through the ConfigCat website all day.
What is an MCP server? The 30-second version
On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to an app or service. This one connects your AI to ConfigCat, so it can look things up and make changes there when you ask. You stay in the chat, and the helper does the clicking behind the scenes.
What this MCP server does
You ask your AI something about your ConfigCat setup, like which feature flags exist in a config or what value a flag has in your test environment. Your AI passes that request to this helper. The helper talks to ConfigCat's management service using the credentials you gave it, and brings the answer back. Your AI then shows it to you in the chat, in normal words or as a small list. If you ask it to change something, like turning a flag on or creating a new one, the helper sends that change to ConfigCat too.
Click to zoomWhat you can do with it
- List your ConfigCat products, configs and environments
- Find feature flags and see their current values
- Create, update or delete feature flags
- Change a flag's value in a specific environment
- Invite team members and adjust their permissions
- Look at audit logs and find stale flags nobody uses
- Get SDK code examples for using a flag in your project
Try asking your AI
- “Show me all feature flags in the checkout config”
- “What is the value of the new-banner flag in production right now?”
- “Create a feature flag called dark-mode in the web config, turned off by default”
- “Which feature flags have not been changed in the last six months?”
- “Give me a JavaScript example of checking the dark-mode flag”
What it gives back to you
You get answers in the chat: lists of flags, products or environments, the current value of a flag, or short summaries of what it found. When you ask for a change, it tells you what it did, like which flag it updated and in which environment. If you ask for code examples, it writes them straight into the chat so you can copy them.
Before you start
What you need
- A ConfigCat account
- Your ConfigCat Management API username and password (you can find them on your ConfigCat account page under public API credentials)
- An AI client that supports MCP, like Cursor, VS Code or the Claude desktop app
- Node.js installed on your computer, since the helper runs through npx
Good to know
It can create, change and delete real things in your ConfigCat account, so check with your AI before letting it apply changes, especially in production environments.
Install it with your AI
Add ConfigCat MCP server to your AI, no technical skills needed
You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.
Sign in to get the install prompt
Members get a ready-made prompt that lets the Claude desktop app check ConfigCat MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.
Who it's for
Developers, product managers and release engineers who use ConfigCat feature flags and want to manage them by chatting instead of clicking.
