Feedbucket

Feedbucket MCP Server lets AI assistants like Claude Code and Cursor manage website feedback from Feedbucket. It runs as a local server that your MCP client connects to, enabling actions such as listing feedback, viewing details, adding comments, and marking items as resolved directly from your AI workflows.

How to use

You run the MCP server locally and connect your MCP client to it. Use the available tools to list, view, comment on, and resolve Feedbucket feedback. Typical usage patterns include retrieving a quick overview of feedback, drilling into a specific item to read full details and logs, adding comments, and resolving items as you progress on your website projects.

How to install

Prerequisites you need before installing the MCP server are a Feedbucket account and Feedbucket installed on your website with protected mode enabled (recommended). Ensure you have access to your website URL and the secret key for protected projects if you will use a protected setup.

Step 1. Install the MCP server globally with npm.

npm install -g feedbucket-mcp

Step 2. Run the setup wizard to configure Claude Code and Cursor for your project. Choose the protected or public flow based on your project type.

Protected projects

feedbucket-setup https://your-website.com YOUR_FEEDBUCKET_SECRET

Public projects

feedbucket-setup https://your-website.com

Step 3. Restart your MCP-enabled IDEs (Claude Code or Cursor) so they load the new MCP server configuration.

Step 4. Confirm the server is working by asking your AI assistant for a quick Feedbucket summary or to list unresolved feedback.

If you prefer to start from a clone of the project, you can clone the repository and install dependencies, then build and run the setup for your site. The commands shown below follow the standard flow.

Additional setup and manual configuration

You can manually configure the MCP server for Claude Code or Cursor by adding an MCP entry that points to the local server script and environment variables.

Manual configuration for Claude Code

{
  "mcpServers": {
    "feedbucket": {
      "command": "node",
      "args": ["/path/to/feedbucket-mcp/dist/index.js"],
      "env": {
        "FEEDBUCKET_PROJECT_ID": "your-project-id",
        "FEEDBUCKET_PRIVATE_KEY": "your-private-key",
        "FEEDBUCKET_API_KEY": "your-api-key"
      }
    }
  }
}

Manual configuration for Cursor

{
  "mcpServers": {
    "feedbucket": {
      "command": "node",
      "args": ["/path/to/feedbucket-mcp/dist/index.js"],
      "env": {
        "FEEDBUCKET_PROJECT_ID": "your-project-id",
        "FEEDBUCKET_PRIVATE_KEY": "your-private-key",
        "FEEDBUCKET_API_KEY": "your-api-key"
      }
    }
  }
}

Environment variables you may set for the MCP server include the following. Provide real values where you have them. If your project uses protected access, you will need the API key in addition to the project ID and private key.

Environment variables and resources

Required environment variables for the MCP server are:

FEEDBUCKET_PROJECT_ID=your-project-id
FEEDBUCKET_PRIVATE_KEY=your-private-key
FEEDBUCKET_API_KEY=your-api-key

Optional: API key is used for protected projects. Keep this value secure and do not share it publicly.

Tools and capabilities

The MCP server provides a suite of tools to interact with Feedbucket feedback from your AI assistants.

Notes on usage and troubleshooting

If you encounter issues loading the MCP server in Claude Code or Cursor, ensure the path to the built distribution is correct and that required environment variables are set. Restart the IDE after changes. If you are using protected projects, verify that the API key and secret are valid and that Feedbucket is configured to require protected access.

Available tools

feedback_list

List and filter feedback with smart summarization

feedback_get

Get full details of a specific feedback item

feedback_stats

Quick project overview (total, resolved, by type, recent activity)

feedback_comment

Add comments to feedback items

feedback_resolve

Mark feedback as resolved

api_status

Check API connection status