Argus Testing - Autonomous QA MCP

An MCP server that tests apps like a real testing engineer - exploring user journeys, discovering unscripted bugs, and proving each finding before reporting it. Its 20 documented tools cover screen, session, observe, file. It runs locally over stdio via the published package.

People connecting browser automation tools to Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-08-09 · ★ 2 · #119 OF 196 MAINTAINED BROWSER AUTOMATION · VERIFIED 2026-08-25

MIT · Python servers · how we verify → /methodology

01 · Install Argus Testing - Autonomous QA MCP

Claude Code

claude mcp add chriswu727-argus -- uvx argus-testing

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "chriswu727-argus": {
      "command": "uvx",
      "args": [
        "argus-testing"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package argus-testing - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.chriswu727 is GitHub-verified and matches the repo owner

03 · What Argus Testing - Autonomous QA MCP can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Capability map

Tools grouped from the project's README - what Argus Testing - Autonomous QA MCP lets an agent do.

Screen

5 tools - e.g. Bind to the foreground or a named macOS app after checking Screen Recording and Accessibility permissions.; Return the foreground app, window title, bounded AX tree, screen coordinates, and a fresh…

start_screen_session · screen_observe · screen_wait_for_stable · screen_screenshot_region · screen_session_status

File

2 tools - e.g. Attach one or more local files to a matching file input.; Dispatch a real file drop onto a matching dropzone.

upload_file · drop_file

read & search

2 tools - e.g. Drain correlated console errors and HTTP 4xx/5xx events captured since the previous read.; Inspect files downloaded during the session, including their paths and sizes.

get_errors · get_downloads

run & execute

1 tool - e.g. Start an exploratory, visual, or regression browser review; optionally accept goals, constraints, and time_budget_minutes; return the one-time protocol and init

start_session

Observe

1 tool - e.g. Return URL, title, description-keyed interactive elements, counts, visible feedback, ARIA tree, and viewport state.

observe

Coverage

1 tool - e.g. Open a goal evidence window with in_progress, then mark it exercised or blocked; terminal states require an explanation and automatically link session evidence.

coverage_update

Click

1 tool - e.g. Click the element best matching a natural-language description; return candidates instead of guessing when ambiguous.

click_what

Verify

1 tool - e.g. Force a fresh load and check whether target text is present or absent. The “Saved!” toast is not proof; this is.

verify_persistence

Latest releases

v0.6.0 · 2026-07-21

Argus 0.6 turns exploratory testing scope into an explicit, evidence-backed coverage contract while reducing the default MCP context footprint. · What changed · Add natural-language testing goals, user constraints, and…

v0.5.1 · 2026-07-21

Argus 0.5.1 makes the autonomous QA MCP easier for people and AI clients to find, install, understand, and trust. · What changed · Unified the PyPI, GitHub, product-page, and official MCP Registry identity around…

v0.5.0 · 2026-07-14

0.5.0 - 2026-07-14 · Argus 0.5 replaces the index-keyed MCP interface with a smaller, · description-keyed workflow and makes evidence preservation part of the · public contract. · Add focused core, screen, and full MCP…

04 · Who maintains Argus Testing - Autonomous QA MCP

Argus Testing - Autonomous QA MCP is maintained by chriswu727. It's the only MCP server we track from this author; the repo dates to Apr 2026.

05 · Facts

category
browser automation - ranked #119 of 196 actively-maintained browser automation servers as of 2026-08-25.
release cadence
3 releases in the last 90 days (latest 2026-07-21)
registry
io.github.chriswu727/argus (active, first published 2026-07-14 · 3 versions)
packages
pypi:argus-testing

06 · Argus Testing - Autonomous QA MCP FAQ

Is Argus Testing - Autonomous QA MCP still maintained?

Yes - as of 2026-08-25, its last commit was 2026-08-09 and it shipped 3 releases in the last 90 days. We re-verify nightly.

What can Argus Testing - Autonomous QA MCP do?

Its README documents 20 tools, including start_session, observe, coverage_update.

How do I install Argus Testing - Autonomous QA MCP?

Run `uvx argus-testing`. You can also paste the ready-made client config above.

Does Argus Testing - Autonomous QA MCP run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Argus Testing - Autonomous QA MCP

More browser automation MCP servers · Churnkey · SAP ABAP MCP · Mat · CometChat Docs

More Python MCP servers · Nautilus Compass · Place Root · Apple Music · Self Hosted AI · Network Sketcher (Local MCP) · see all