Skip to main content
Glama
enesjakozh
zueai

Frontend Review MCP

by zueai
OverviewSchemaRelated ServersScoreDiscussions
JavaScript
Local

frontend-review-mcp

An MCP server that performs a visual review of a UI edit request. Ask your agent to screenshot the page before and after the edit, and then call this tool to review the edit.

Usage

Cursor

  • To install in a project, add the MCP server to your .cursor/mcp.json:

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

		}
	}
}

  • To install globally, add this command to your Cursor settings:

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

Windsurf

  • 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>"]
		}
	}
}

Related MCP server: MCP PDF Forms

Tools

Currently, the only tool is reviewEdit.

Your Agent will call this tool with the following arguments:

  • beforeScreenshotPath: The absolute path to the screenshot of the page before the edit.

  • afterScreenshotPath: The absolute path to the screenshot of the page after the edit.

  • editRequest: A detailed description of the UI edit request made by the user.

The tool will return a response with either a yes or no response, indicating whether the edit visually satisfies the edit request. If no, it will provide a detailed explanation of why the edit does not satisfy the request so you can continue to work on it.

Review Model

Currently, the review model is Qwen/Qwen2-VL-72B-Instruct from Hyperbolic. It will automatically retry the request with these models if it fails:

Fallback order:

  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

If you want to use a different model as the first model, you can add the MODEL arg to the command:

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

It will try the specified model first, and then try the others if it fails.

Taking Screenshots

You can use any MCP server to take screenshots. I've been using https://github.com/AgentDeskAI/browser-tools-mcp which has a takeScreenshot tool, among other useful tools for frontend development.

AI Instructions

You can include the following instructions in your AI's prompt to make it take screenshots and review the edit:

When making frontend edits:

- Before making any changes, call the mcp_takeScreenshot function to save the current state of the page.
- After making your change, call the mcp_takeScreenshot function again to save the new state of the page.
- Screenshots will be saved to /screenshots folder.
- Run this command to get the absolute paths of the 2 most recent screenshots in the /screenshots folder:



find screenshots -type f -name "*.png" -exec stat -f "%m %N" {} \; | sort -nr | head -n 2 | awk '{print $2}' | xargs realpath | awk 'NR==1 {print "before path: ", $0} NR==2 {print "after path: ", $0}'


- Call the mcp_reviewEdit function to have your changes visually reviewed.
- Use the following format for the tool call:

{
  "beforeScreenshotPath": string, // Absolute path to the second-most recent screenshot
  "afterScreenshotPath": string, // Absolute path to the most recent screenshot
  "editRequest": string // Describe the edit request from the user in a couple of sentences
}

- You should summarize my edit request into a couple of sentences so that the frontend reviewer understands the changes you made.

- The tool will either return "yes" if your changes are good, or "no" with a brief explanation if the changes don't satisfy the edit request. Keep editing with the same process until the reviewer returns "yes".

Tips

Make sure YOLO mode is on and MCP tools protection is off in your Cursor settings for the best experience.

Available Tools

1 tool
reviewEditB

Perform a visual review of a UI edit request. The 'before screenshot' is a screenshot of the page before the edit, and the 'after screenshot' is the screenshot of the page after the edit. You will recieve either a yes or no response, indicating whether the edit visually satisfies the edit request. If no, it will provide a detailed explanation of why the edit does not satisfy the request so you can continue to work on it.

ParametersJSON Schema
NameRequiredDescriptionDefault
afterScreenshotPathYesAbsolute path to the 'after' screenshot file (png)
beforeScreenshotPathYesAbsolute path to the 'before' screenshot file (png)
editRequestYesA detailed description of the UI edit request made by the user. Do not describe the changes you made, but just summarize what the user asked you to change on the page.

TDQS

B3.4/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full behavioral disclosure burden. It describes the core behavior (visual review returning yes/no with explanations) and the iterative nature ('continue to work on it'). However, it doesn't disclose important behavioral traits like processing time, file size limitations, authentication needs, error conditions, or what constitutes a valid screenshot.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is appropriately sized (3 sentences) and front-loaded with the core purpose. Each sentence adds value: first states purpose, second explains parameters, third describes outcomes. There's minimal redundancy, though the second sentence could be slightly more concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter tool with no annotations and no output schema, the description provides adequate but incomplete context. It covers the basic workflow and outcome format but lacks details about error handling, performance characteristics, or what specific visual criteria are used for evaluation. The absence of output schema means the description should ideally explain return values more thoroughly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, providing complete parameter documentation. The description adds minimal value beyond the schema: it clarifies that screenshots represent 'before' and 'after' states and mentions the edit request context. However, it doesn't provide additional semantic context about parameter relationships or usage nuances beyond what's already in the schema descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Perform a visual review of a UI edit request' with specific resources (before/after screenshots) and verb (review). It explains what the tool does (evaluates if edit satisfies request) and the outcome (yes/no with explanation). However, without sibling tools, it cannot demonstrate differentiation from alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage context: when you have UI edit screenshots and need validation. It mentions 'so you can continue to work on it' suggesting iterative improvement workflow. However, there's no explicit guidance on when to use this tool versus other validation methods or prerequisites for effective use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.4/5.0
Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The tool has a clear, singular purpose focused on visual review of UI edits.

Naming Consistency5/5

Since there is only one tool, naming consistency is inherently perfect. The tool name 'reviewEdit' follows a clear verb_noun pattern and stands alone without any conflicting conventions.

Tool Count2/5

A single tool is too few for a server named 'Frontend Review MCP', which suggests a broader scope for frontend review tasks. This minimal toolset feels thin and incomplete for the implied domain.

Completeness2/5

The tool surface is severely incomplete for frontend review. It only covers visual validation of UI edits, lacking tools for other aspects like accessibility checks, performance reviews, code analysis, or comparison of multiple edits, which are typical in this domain.

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/zueai/frontend-review-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server