Frontend Review MCP server

Integrates with Hyperbolic's AI models to perform visual reviews of UI edit requests, providing automated visual QA for frontend development workflows.
Back to servers
Setup instructions
Provider
zueai
Release date
Feb 27, 2025
Language
TypeScript
Package
Stats
710 downloads
26 stars

This MCP server helps review UI changes by comparing before/after screenshots of a page. It uses vision models to evaluate whether your edits visually satisfy the requested changes, providing feedback for further improvements if needed.

Installation

Cursor Installation

You can install the MCP server in a specific project or globally:

Project-specific installation:

  • Add the MCP server to your .cursor/mcp.json file:
{
    "mcpServers": {
        "frontend-review": {
            "command": "npx",
            "args": ["frontend-review-mcp HYPERBOLIC_API_KEY=<YOUR_API_KEY>"]
        }
    }
}

Global installation:

  • Add this command to your Cursor settings:
npx frontend-review-mcp HYPERBOLIC_API_KEY=<your-hyperbolic-api-key>

Windsurf Installation

  • Add the MCP server to your ~/.codeium/windsurf/mcp_config.json file:
{
    "mcpServers": {
        "frontend-review": {
            "command": "npx",
            "args": ["frontend-review-mcp HYPERBOLIC_API_KEY=<YOUR_API_KEY>"]
        }
    }
}

Using the Frontend Review Tool

The server provides a tool called reviewEdit that compares before and after screenshots of your UI to evaluate changes.

Tool Parameters

Your agent will call this tool with these arguments:

  • beforeScreenshotPath: Absolute path to the screenshot before the edit
  • afterScreenshotPath: Absolute path to the screenshot after the edit
  • editRequest: Description of the UI edit request made by the user

Review Models

By default, the tool uses Qwen/Qwen2-VL-72B-Instruct from Hyperbolic, with automatic fallbacks if needed:

  1. Qwen/Qwen2-VL-72B-Instruct
  2. Qwen/Qwen2-VL-7B-Instruct
  3. meta-llama/Llama-3.2-90B-Vision-Instruct
  4. mistralai/Pixtral-12B-2409

To specify a different initial model, add the MODEL argument:

npx frontend-review-mcp HYPERBOLIC_API_KEY=<your-hyperbolic-api-key> MODEL=<your-model>

Taking Screenshots

You'll need to take screenshots for comparison. The browser-tools-mcp server provides a takeScreenshot tool that works well with this review tool.

Workflow Example

Here's a suggested workflow for your AI agent:

  1. Take a screenshot before making any changes
  2. Make the requested UI changes
  3. Take another screenshot after the changes
  4. Get the absolute paths of both screenshots
  5. Call the reviewEdit tool with these paths and a description of the edit
  6. If the review returns "no", continue editing until it returns "yes"

Cursor Settings Tips

For the best experience, make sure:

  • YOLO mode is turned on
  • MCP tools protection is turned off

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "frontend-review" '{"command":"npx","args":["frontend-review-mcp","HYPERBOLIC_API_KEY=<YOUR_API_KEY>"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "frontend-review": {
            "command": "npx",
            "args": [
                "frontend-review-mcp",
                "HYPERBOLIC_API_KEY=<YOUR_API_KEY>"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "frontend-review": {
            "command": "npx",
            "args": [
                "frontend-review-mcp",
                "HYPERBOLIC_API_KEY=<YOUR_API_KEY>"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later