Complete AI Training

MCP server · Developer tools · official

Featureflip MCP server

by canopy-labs · official

Let your AI create, toggle, and clean up Featureflip feature flags right from your chat.

Flow diagram: you ask your AI “Turn off the new checkout flag in staging”, the Featureflip MCP server connects it to Featureflip, and you get back confirmation in your chat.

This is a helper made by Featureflip, the service teams use to turn features on and off without releasing new code. Once you connect it to your AI assistant, you can ask in plain words to create a flag, switch it off, or find old ones worth removing. It is handy for developers and product people who already use Featureflip and want to skip clicking around the dashboard.

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 one new skill or one connection to an outside service. This one connects your AI to Featureflip, so when you ask about a flag, the AI can actually look it up or change it there for you. You do not need to understand how it works inside; you just add it once and then talk to your AI like usual.

What this MCP server does

You ask your AI something like 'turn off the new checkout flag in staging'. The AI passes that request to this helper program. The helper signs in to Featureflip with your token and does the work there, like creating the flag or flipping it off. Then it sends the result back, and your AI tells you in the chat what happened. Every change is logged in Featureflip and tied to your token, so there is a record.

Flow diagram: you ask your AI “Turn off the new checkout flag in staging”, the Featureflip MCP server connects it to Featureflip, and you get back confirmation in your chat. Click to zoom

What you can do with it

  • List your projects, environments, and feature flags
  • Create a new flag and get the code snippet to use it
  • Toggle a flag on or off in a chosen environment
  • Edit who a flag is shown to with targeting rules
  • Find flags that look stale and are good cleanup candidates
  • Set an expiry date or an owner on a flag
  • Archive, restore, or delete a flag

Try asking your AI

  • “List all feature flags in the checkout project”
  • “Create a flag called new-pricing-page and turn it off in production”
  • “Show me flags that have not changed in months and might be stale”
  • “Turn on the dark-mode flag for 10 percent of users in staging”

What it gives back to you

You get answers in the chat, like a list of flags with their current state, or a short confirmation that a flag was created or toggled. When you ask for a new flag, it can also give you the code snippet to paste into your app. For cleanup questions, it gives you a list of flags that look unused. Nothing shows up as a separate file; it is all text in the conversation.

Before you start

What you need

  • A Featureflip account
  • An API token from your Featureflip settings (a kind of password for apps; the dashboard gives you one)
  • Node.js installed on your computer (the free tool that runs the helper)

Good to know

This helper can create, change, and delete feature flags in your real Featureflip account, so double-check before you confirm a change that affects production.

Install it with your AI

Add Featureflip 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 Featureflip 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.

Sign in Become a member

Who it's for

Developers, QA engineers, and product managers who already use Featureflip and want to manage flags without leaving their AI assistant.