Webevalagent MCP Server

The MCP server of operative.sh is an LLM-driven autonomous debugging tool that can execute and debug web applications directly in the code editor.

Developer tools Browser automation #Intelligent Debugging #Web Testing #Automation Tool .Python

rating : 0 points

downloads : 6.8K

update time : 2025-04-28

Open Site

What is the MCP Server?

The MCP server is an AI-based tool that enables developers to autonomously execute and debug web applications within the code editor. By simulating a real environment, the MCP server can quickly identify and fix errors in the code, enhancing development efficiency.

How to use the MCP Server?

First, you need to install and configure the MCP server. Then, enable the relevant plugin in the code editor to start debugging your web application.

Applicable Scenarios

The MCP server is suitable for any scenario that requires frequent debugging of web applications, especially complex front - end projects and cross - platform development.

Main Features

Network Traffic Capture

Automatically record and analyze all network requests and responses to help developers quickly locate problems.

Browser Navigation

Efficiently test web applications through simulated browser operations.

Console Error Collection

Capture error logs in the JavaScript console in real - time to ensure no omissions.

Autonomous Debugging

Automatically detect and fix potential problems in the code using AI algorithms.

Advantages

Significantly improve development efficiency

Reduce manual debugging time

Support multiple programming languages and frameworks

Easy to integrate into existing workflows

Limitations

Initial setup may be complex

Dependent on a stable network connection

Some advanced features may require a paid subscription

How to Use

Get an API Key

Visit the official website of operative.sh to register an account and obtain an API key.

Install the MCP Server

Run the installation script to complete the deployment of the MCP server.

Enable the Plugin

Enable the web_eval_agent plugin in the code editor.

Usage Examples

Case Title: Network Traffic Capture

Demonstrate how to use the MCP server to capture network requests for a specific page.

Case Title: Console Error Detection

Show how to use the MCP server to detect JavaScript errors on a page.

Frequently Asked Questions

Is the MCP server free to use?

How to solve problems that occur during the installation process?

Which operating systems does the MCP server support?

Related Resources

Official Website

Learn more information and the latest news.

GitHub Repository

View the source code and contribute to the code.

Tutorial Video

Watch the tutorial on using the MCP server.

🚀 operative.sh web-eval-agent MCP Server

Let the code fix itself. You've got better things to do.

🚀 Quick Start

The MCP server of operative.sh automates the execution and debugging of web applications through an LLM-powered agent, directly within your code editor.

✨ Features

This powerful tool will revolutionize your development experience in Code IDEs (Cline, Cursor):

🌐 Browse Your Web App: Use BrowserUse (2x faster with the MCP backend).
📊 Capture Network Traffic: Keep track of all requests and responses.
🚨 Collect Console Errors: No error can hide.
🤖 Automated Debugging: The Cursor agent calls the web QA agent on the MCP server to test if the code functions end-to-end as expected.

📦 Installation

🏁 Quick Start (macOS/Linux)

Prerequisites: Install brew: /bin/bash -c "$(curl -fsSL https://raw.githubusercontent.com/Homebrew/install/HEAD/install.sh)", npm: (brew install npm), and jq: brew install jq.
After getting your free API key here, run the installer:

# Feel free to review the installation script content:
# curl -LSf https:// operative .sh/install.sh | less -N
# Download, install, and remove the installation script
curl -LSf https://operative.sh/install.sh -o install.sh && bash install.sh && rm install.sh

Enable Cursor agent mode with web_eval_agent (make sure to refresh or restart Cursor).
If you encounter any issues, refer to the troubleshooting section below.

🛠️ Manual Windows Installation (Cline)

# 1. Get your API key at operative.sh.
# 2. Install uv (curl -LsSf https://astral.sh/uv/install.sh | sh).
# 3. uvx --from git+https://github.com/Operative-Sh/web-eval-agent.git playwright install.
# 4. Enable the Cline agent with web_eval_agent (you may need to restart Cline).

⚠️ Important Note

There were initial issues with the tool calling Playwright, which have been fixed. Please update to the latest version (released on 4/14). It is recommended to run npm install -g playwright to resolve the issue.

If you have any problems, feel free to submit an issue in this repository here!

Sincerely made by @ operative.sh