Argus is an MCP server. It adds evidence-first browser QA to Claude Code, Codex, Cursor, or any MCP host without taking over the host agent's identity or broader coding task. The agent explores…
argus is an MCP project maintained in the chriswu727/argus repository. The maintainer describes its purpose as “Argus is an MCP server. It adds evidence-first browser QA to Claude Code, Codex, Cursor, or any MCP host without taking over the host agent's…”. Read the project documentation for the complete scope.
The documented pypi package is argus-testing. The configuration below comes from the maintainer’s example; adapt its paths and account values to your environment.
Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.
Check the linked publisher documentation and your connected client's tool list. Names and availability can vary with the server version and account permissions.
| Tool | What it does |
|---|---|
| Profile | Public tools |
| core | 30 |
| screen | 14 |
| full | 77 |
| Tools | Purpose |
| start_session | Start an exploratory, visual, or regression browser review; optionally accept goals, constraints, and time_budget_minutes; return the one-time protocol and… |
| observe | Return URL, title, description-keyed interactive elements, counts, visible feedback, ARIA tree, and viewport state. |
| coverage_update | Open a goal evidence window with in_progress, then mark it exercised or blocked; terminal states require an explanation and automatically link session… |
| click_what | Click the element best matching a natural-language description; return candidates instead of guessing when ambiguous. |
| upload_file | Attach one or more local files to a matching file input. |
| get_errors | Drain correlated console errors and HTTP 4xx/5xx events captured since the previous read. |
| verify_persistence | Force a fresh load and check whether target text is present or absent. The “Saved!” toast is not proof; this is. |
| regression_check | Re-test journaled findings for the current origin without requiring another discovery pass. |
| end_session | Close the active session and emit HTML, JSON, JUnit, and SARIF reports. |
| start_screen_session | Bind to the foreground or a named macOS app after checking Screen Recording and Accessibility permissions. |
| screen_observe | Return the foreground app, window title, bounded AX tree, screen coordinates, and a fresh screenshot. |
| screen_wait_for_stable | Wait until the target window remains visually stable within a configurable threshold. |
| screen_screenshot_region | Capture a precise rectangular screen region for fine visual evidence. |
| screen_session_status | Report elapsed time, remaining session budget, action counts, and the abort-file path. |
| emulate_media | Emulate dark/light color schemes and reduced-motion preferences. |
| drop_file | Dispatch a real file drop onto a matching dropzone. |
| set_dialog_handler | Queue an accept, dismiss, or prompt response for the next JavaScript dialog. |
| eval_js | Run arbitrary page-context JavaScript. It remains disabled unless the server also starts with --unsafe. |
| get_downloads | Inspect files downloaded during the session, including their paths and sizes. |
| crawl_site | Crawl bounded internal pages and collect browser events, link results, and performance evidence. |
{
"mcpServers": {
"argus": {
"command": "uvx",
"args": [
"--from",
"argus-testing",
"argus-mcp"
]
}
}
}From the project documentation. Replace placeholders and example paths before connecting.
Use Microsoft’s Playwright MCP server to navigate pages, inspect accessibility snapshots, fill forms and capture browser screenshots.
The original Chromium automation reference server — simple, screenshot-driven browser control.
Give your coding agent the full DevTools toolbox: traces, network, console, heap snapshots and Lighthouse.
Puppeteer-powered browser control that drives pages from the accessibility tree instead of pixels.
Enables AI-powered applications to monitor and interact with browser data via a Chrome extension and MCP.
Automates browsers and APIs, enabling Large Language Models (LLMs) to interact with web pages for tasks like screenshot capture and JavaScript