Log inSubmit server
Argus logo

Argus

Evidence-first browser QA that explores user journeys, verifies findings from clean loads, and produces reproducible bug reports.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Argus

Pick your client, then add it in one click or paste the config.

STDIOPython
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "argus": {
      "command": "uvx",
      "args": [
        "--from",
        "argus-testing",
        "argus-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 28 tools correctly (11d ago).

Overview

Argus MCP server gives coding agents an evidence-first workflow for exploratory browser testing and reproducible bug reporting. It drives browser interactions through description-keyed tools, tracks testing goals, captures evidence, and independently rechecks suspected bugs after a clean page load. Reports can distinguish verified findings from observations and export HTML, JSON, JUnit, or SARIF. Reach for it when an agent needs to investigate an app beyond predefined test scripts, with optional native macOS screen testing.

Use cases

  • Explore a local web app for unscripted bugs
  • Verify suspected browser failures after a clean reload
  • Track coverage across scoped testing goals
  • Export findings for CI or issue triage
  • Test native macOS applications through the screen profile

Key features

  • Exploratory browser testing
  • Clean-load persistence verification
  • Description-keyed interaction tools
  • Goal and coverage tracking
  • HTML, JSON, JUnit, and SARIF reports
  • Optional native macOS screen testing

Tools28

What Argus lets your agent do. Expand a tool for its parameters.

Verified live~2.5k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

11/11 checks healthy over the last 58d

What it can do

From the 28 tools this server returned when we ran it; 28 declare their own safety hints.

Can delete or modify data · 16Writes files · 1Handles credentials · 2Makes network requests · 24Read-only tools · 12
Network at startup2 connections
Files written at startup10

Observed 2026-10-28 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 16d ago via OSV.dev · argus-testing (PyPI)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars5Stargazers on the source repository.
Last commit3d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed28Callable tools this server registers over MCP.

How Argus works

What Argus MCP server does

Argus MCP server adds exploratory quality assurance to an MCP host. An agent can provide an application URL, describe testing goals and constraints, then investigate user journeys through browser interactions. The workflow is intended to uncover unscripted problems rather than execute only a fixed test case.

Each suspected issue is treated as a finding that needs evidence. Argus records the relevant actions, pages, screenshots, observations, and persistence checks. A finding is marked as verified only when the specified symptom is seen again after the page is loaded from a clean state. Findings that are merely observed or remain inconclusive stay separate from verified bugs.

How it works

The host agent supplies the testing judgment while Argus provides the testing protocol and state. A session can begin with explicit goals, constraints, and an advisory time budget. The server keeps the current goals and discovered pages available to later observations, so the agent can see what has been covered and what remains.

A goal can be marked in progress before its journey starts. Later coverage updates mark it exercised or blocked and require an explanation. Argus links the testing window to URLs, redacted action values, screenshots, persistence checks, bugs, and other observations. This coverage information is retained in the final reports, including unfinished goals, rather than implying that an incomplete session was comprehensive.

For persistence checks, the clean load retains authentication and browser storage by default. Replaying a journey can repeat real writes, so test targets should be chosen with that behavior in mind. The resulting receipt confirms the specified visible symptom; it does not establish every possible root cause.

Setup and configuration

Install Chromium once with uvx --from playwright playwright install chromium, then register the package as an MCP server. A standard stdio configuration can launch uvx --from argus-testing argus-mcp; the package can also be installed with pip before running argus-mcp.

The default core tool profile exposes the primary web-testing workflow. Use --list-tools to inspect the selected profile, --tool-profile screen for native macOS testing, or --tool-profile full for the complete advanced surface. ARGUS_TOOL_PROFILE provides the profile setting through the environment. The optional monitor can be enabled with --monitor-port or ARGUS_MONITOR_PORT; it is disabled by default.

Tools and capabilities

The tool surface uses descriptions instead of unstable numeric element references. For example, an agent can request click_what("Login button"). The documented workflow includes session setup, observation, described actions, persistence verification, and coverage updates.

Argus stores screenshots in separate run directories and keeps bounded event data for long browser sessions. It can inspect eligible API response bodies while skipping binary or oversized content before it enters memory. Reports are available in HTML, JSON, JUnit, and SARIF formats. A local monitor can expose session state, progress, calls, failures, findings, recent events, health checks, server-sent events, and Prometheus metrics.

The optional screen profile supports native macOS applications through the Accessibility tree, including apps such as Notes, Cursor, and Safari. It uses the same description-keyed interaction style and does not require headless Chrome for that mode.

Limitations and notes

Argus MCP server is not an authenticated remote monitoring service. Its monitor binds to 127.0.0.1, should not be placed behind a public proxy, and exposes status rather than action endpoints. Monitoring output excludes page contents, URLs, typed values, screenshots, and tool arguments.

Evidence retention is bounded. Network, error, download, dialog, and response-body limits can discard older evidence; the server reports such drops in tool output and the final session summary. Cleanup is explicit and dry-run by default, while .argus journals and state capsules are protected.

The macOS screen workflow requires Screen Recording and Accessibility permissions, and the setup documents cliclick as a coordinate and keystroke fallback. Reproduction checks validate the recorded symptom, not its root cause, and replay may perform real application writes.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Argus

Argus is an MCP server that connects coding agents to browser-based QA workflows and, through its screen profile, native macOS applications. Its main tools support exploratory observation, description-keyed actions such as clicking named controls, goal coverage updates, persistence verification, evidence capture, and reports that separate independently verified bugs from unconfirmed observations.

Install Chromium with `uvx --from playwright playwright install chromium`, then register `uvx --from argus-testing argus-mcp` with your MCP client. You can alternatively install `argus-testing` with pip and run `argus-mcp` directly.

Yes, Argus works with Cursor through its MCP configuration. The README provides a Cursor installation link and says to install Chromium once before the first test.

Yes, Argus can test native macOS applications with the `screen` tool profile. This mode uses the Accessibility tree, requires Screen Recording and Accessibility permissions, and documents `cliclick` as a fallback for keystrokes and coordinates.

Related MCP servers

All in Browser Automation All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewArgus AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/argus?style=directory)](https://allmcps.com/mcp/argus)
HTML Embed
<a href="https://allmcps.com/mcp/argus"><img src="https://allmcps.com/api/badge/argus?style=directory" alt="Argus on AllMCPs" /></a>