operative_sh/web-eval-agent
Apache-2.0API key required🐍 🏠 🍎 - An MCP Server that autonomously debugs web applications with browser-use browser agents
Install
uvx --withRequired environment variables
OPERATIVE_API_KEYSet in your MCP configYOUR_KEYSet in your MCP configclaude_desktop_config.json
{
"mcpServers": {
"operative-sh-web-eval-agent": {
"command": "uvx",
"args": [
"--with"
],
"env": {
"OPERATIVE_API_KEY": "<YOUR_OPERATIVE_API_KEY>",
"YOUR_KEY": "<YOUR_YOUR_KEY>"
}
}
}
}Add this to your Claude Desktop config file. Find it at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS.
What this does
operative_sh/web-eval-agent exposes a set of tools to Claude over the Model Context Protocol. After you add it to claude_desktop_config.json (snippet above) and restart Claude Desktop, those tools become callable inside any conversation. That makes it useful when you want Claude to reach into live web pages and browser sessions without copy-pasting context every turn.
Requirements
This server needs the following environment variables to be set before it can run:
OPERATIVE_API_KEY YOUR_KEY
Set these via the env object in your MCP config (see claude_desktop_config.json snippet above).
Common use cases
- •Navigate, fill forms, and scrape pages on demand from Claude
- •Test UI flows or capture screenshots as part of a debugging session
- •Reach data behind logins or interactive pages that simple HTTP fetch cannot
More Python MCP servers
microsoft/markitdown
🎖️ 🐍 🏠 - MCP tool access to MarkItDown -- a library that converts many file formats (local or remote) to Markdown for LLM consumption.
mindsdb/mindsdb
Connect and unify data across various platforms and databases with .
microsoft/playwright-mcp
Official Microsoft Playwright MCP server, enabling LLMs to interact with web pages through structured accessibility snapshots
agent-infra/mcp-server-browser
📇 🏠 - Browser automation capabilities using Puppeteer, both support local and remote browser connection.