๐ Operative.sh Web QA Agent MCP Server
An MCP server that evaluates web applications.
Operative-Sh
README
๐ Operative.sh WebEvalAgent MCP Server
Let the code fix itself, you've got better things to do.
๐ฅ Supercharge Your Debugging
operative.sh's MCP Server unleashes LLM-powered agents to autonomously execute and debug web apps directly in your code editor.
โก Features
This weapon in your development arsenal transforms your Code IDE experience (Cline, Cursor):
- ๐ Navigate your webapp using BrowserUse (now 2x FASTER when using our backend!)
- ๐ Capture network traffic - all requests/responses at your fingertips
- ๐จ Collect console errors - nothing escapes detection
- ๐ค Autonomous debugging - the Cursor agent calls the web QA agent mcp server to test if the code it wrote works as epected end-to-end.
๐ Quick Start (macOS/Linux)
# 1. Get your API key at operative.sh
# 2. Run the installer
bash -i <(curl -LSf https://operative.sh/webevalqa/install.sh)
# 3. Unleash the agent in Cursor Agent Mode with web_app_ux_evaluator (may have to restart Cursor)
๐ ๏ธ Install in Cursor Agent with Single Command
API_KEY="your-api-key-here" && jq --arg k "$API_KEY" '.mcpServers["web-eval-agent"]={"command":"uvx","args":["--from","git+https://github.com/Operative-Sh/web-eval-agent.git","webEvalAgent"],"env":{"OPERATIVE_API_KEY":$k}}' ~/.cursor/mcp.json > ~/.cursor/mcp.json.tmp && mv ~/.cursor/mcp.json.tmp ~/.cursor/mcp.json
๐ ๏ธ Manual JSON Installation
- Run
uvx --from git+https://github.com/Operative-Sh/web-eval-agent.git webEvalAgent
with no api key first since Cursor doesn't wait for our deps to download! - On startup, kill and then update your relevent MCP JSON:
"web-eval-agent": {
"command": "uvx",
"args": [
"--from",
"git+https://github.com/Operative-Sh/web-eval-agent.git",
"webEvalAgent"
],
"env": {
"OPERATIVE_API_KEY": "YOUR_API_KEY"
}
}
๐ ๏ธ 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. Unleash the agent in Cline with web_app_ux_evaluator (may have to restart Cline)
๐จ Issues
- Any issues feel free to open an Issue on this repo!
Built with <3 @ operative.sh
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
MCP Package Docs Server
Facilitates LLMs to efficiently access and fetch structured documentation for packages in Go, Python, and NPM, enhancing software development with multi-language support and performance optimization.
Claude Code MCP
An implementation of Claude Code as a Model Context Protocol server that enables using Claude's software engineering capabilities (code generation, editing, reviewing, and file operations) through the standardized MCP interface.
@kazuph/mcp-taskmanager
Model Context Protocol server for Task Management. This allows Claude Desktop (or any MCP client) to manage and execute tasks in a queue-based system.
Linear MCP Server
Enables interaction with Linear's API for managing issues, teams, and projects programmatically through the Model Context Protocol.
mermaid-mcp-server
A Model Context Protocol (MCP) server that converts Mermaid diagrams to PNG images.
Jira-Context-MCP
MCP server to provide Jira Tickets information to AI coding agents like Cursor

Linear MCP Server
A Model Context Protocol server that integrates with Linear's issue tracking system, allowing LLMs to create, update, search, and comment on Linear issues through natural language interactions.

Sequential Thinking MCP Server
This server facilitates structured problem-solving by breaking down complex issues into sequential steps, supporting revisions, and enabling multiple solution paths through full MCP integration.