Operative Web Eval Agent

MCPOfficialOpen SourceApache-2.080.3

by Operative-Sh • Testing & QA

An MCP server that launches a browser-driven agent to autonomously test, debug, and evaluate web apps by capturing screenshots, network requests, and console logs.

Example Use Cases

1
Autonomously run end-to-end UX tests and flows (e.g., signup, API key deletion) and report usability issues.
2
Collect and return network requests and console/error logs while exercising an app to aid debugging.
3
Reuse interactive browser authentication state (cookies/localStorage) across runs for testing authenticated flows.

Description

This MCP server runs a BrowserUse-powered agent (with an operative.sh backend) to navigate web apps, execute user-defined test tasks, and produce rich UX evaluation reports. It captures network traffic and console errors, takes screenshots/screencasts, and can persist browser state (cookies/localStorage) for authenticated flows. Provided tools include web_eval_agent for automated evaluations and setup_browser_state for interactive sign-in and state reuse, making end-to-end debugging and QA faster and more reproducible.

Quick Actions

View on GitHub

Security

Scanned 3 month(s) ago

Risk Level

MINIMAL

Read-only data retrieval, no side effects

Trust Score

C53/100

6/17 checks passed

Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.

Quick Stats

Service TypeMCP

Pricing ModelFree

Capabilities0 Tools / 0 Prompts / 0 Resources

OwnerOperative-Sh

CategoryTesting & QA

DependenciesStandalone