With Bucket's MCP you can flag features directly from the chat window in your code editor. Whether that’s VS Code, Cursor, Windsurf, Claude Code—any IDE that has MCP support.
For example, if you’ve built a “Download CSV” feature and want to flag it, you no longer have to go to bucket.co or use the CLI to create a feature key. Instead, ask the MCP to do it for you: “flag the download button with bucket.”
You can also use the MCP to grant company segments and individual companies or users access to the feature—straight from the chat window. To give “Acme” access, for example, you’d ask something like: “give Acme access to the download csv feature” and Bucket will look up the company name and enable the Download CSV feature for it.
To get started, add the Bucket MCP in your IDE.
まだレビューはありません. 最初のレビューを投稿しましょう！
会話に参加するにはサインインしてください
Highlight AIInitialize a new Bucket configuration in your project. This creates a `bucket.config.json` file with your settings and prompts for any required information not provided via options.
All-in-one command to get started quickly. Combines `init`, feature creation, and type generation in a single step.
Log in to your Bucket account. This will authenticate your CLI for subsequent operations and store credentials securely.
Log out from your Bucket account, removing stored credentials.
Create a new feature in your Bucket app. Guides you through the feature creation process with interactive prompts.
List all features for the current app, helping you visualize what features are available and their current configurations.
Generate TypeScript types for your features, ensuring type safety when using Bucket features in your TypeScript/JavaScript applications.
List all companies in your app, providing a table with company details.
Grant or revoke access to specific features for companies, segments, and users.
Set up AI-specific rules for your project to enable AI tools to better understand how to work with Bucket and feature flags.
Configure your editor or AI client to connect with Bucket's remote MCP server, allowing AI tools to understand your feature flags.
