🚀 operative.sh web-eval-agent MCP Server

Created By
Operative-Sha year ago
An MCP server that autonomously evaluates web applications.
Overview

What is the Operative.sh Web Eval Agent?

The Operative.sh Web Eval Agent is an MCP server designed to evaluate and debug web applications using LLM-powered agents that operate directly within your code editor.

How to use the Operative.sh Web Eval Agent?

To use the Web Eval Agent, obtain your API key from operative.sh, run the installer, and unleash the agent in Cursor Agent Mode with the command 'web_app_ux_evaluator'.

Key features of the Operative.sh Web Eval Agent?

  • 🌐 Navigate your web app using BrowserUse, now 2x faster with the backend.
  • 📊 Capture network traffic, providing access to all requests and responses.
  • 🚨 Collect console errors to ensure nothing escapes detection.
  • 🤖 Autonomous debugging capabilities that test code end-to-end.

Use cases of the Operative.sh Web Eval Agent?

  1. Debugging web applications efficiently in real-time.
  2. Capturing and analyzing network traffic for performance optimization.
  3. Automating the testing process to ensure code quality.

FAQ from the Operative.sh Web Eval Agent?

  • Can the Web Eval Agent debug any web application?

Yes! It is designed to work with various web applications seamlessly.

  • Is there a cost associated with using the Web Eval Agent?

The details regarding pricing can be found on the operative.sh website.

  • What platforms does the Web Eval Agent support?

It supports macOS and Linux environments.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
Operative-Sh
Star
973
Language
Python
License
Apache-2.0 license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago