Argus
Argus hooks Chrome DevTools Protocol to run full QA sweeps on web apps without writing test scripts. It exposes six tools: argus_audit for fast scans (JS errors, network failures, a11y, SEO, security), argus_audit_full for deep passes with Lighthouse scoring and memory leak detection, argus_compare to diff dev against staging with side-by-side screenshots, and argus_get_context to snapshot everything broken on the current tab for Claude to diagnose. You launch Chrome with remote debugging on port 9222, point it at your local or staging URL, and ask Claude to run an audit. Reports post to Slack or generate a standalone HTML dashboard. Built for catching runtime exceptions, API double-fetch bugs, CSS cascade conflicts, and responsive layout regressions before they ship.
- GitHub stars
- 5
- tools
- 9
- auth
- Secret needed
- transport
- STDIO
- env vars
- 5
- last updated
- Jul 18, 2026
Tools
9 toolsPublic tool metadata for what this MCP can expose to an agent.
argus_auditFast pass — JS, network, accessibility, SEO, security, CSS, content
Fast pass — JS, network, accessibility, SEO, security, CSS, content
No parameter schema in public metadata yet.
argus_audit_fullDeep pass — adds Lighthouse, responsive checks, memory leak detection, hover-state bugs
Deep pass — adds Lighthouse, responsive checks, memory leak detection, hover-state bugs
No parameter schema in public metadata yet.
argus_compareDiff dev vs staging — screenshots, findings delta, environment regressions
Diff dev vs staging — screenshots, findings delta, environment regressions
No parameter schema in public metadata yet.
argus_get_contextCapture everything broken on the open tab — with resolved / new / persisting diff vs the last snapshot (the fix loop)
Capture everything broken on the open tab — with resolved / new / persisting diff vs the last snapshot (the fix loop)
No parameter schema in public metadata yet.
argus_watch_snapshotSnapshot the open tab without navigating (preserves auth/form state)
Snapshot the open tab without navigating (preserves auth/form state)
No parameter schema in public metadata yet.
argus_last_reportReturn last JSON report without re-running
Return last JSON report without re-running
No parameter schema in public metadata yet.
argus_design_auditFigma URL → 13 design-token finding types (color, spacing, typography, shadows, etc.)
Figma URL → 13 design-token finding types (color, spacing, typography, shadows, etc.)
No parameter schema in public metadata yet.
argus_visual_diffScreenshot baseline comparison. Pass updateBaseline: true to reset.
Screenshot baseline comparison. Pass updateBaseline: true to reset.
No parameter schema in public metadata yet.
argus_pr_validateFetch GitHub PR diff → map changed files to affected routes → targeted audit → baseline-aware block decision + idempotent PR comment + Check Run
Fetch GitHub PR diff → map changed files to affected routes → targeted audit → baseline-aware block decision + idempotent PR comment + Check Run
No parameter schema in public metadata yet.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageConfiguration
TARGET_DEV_URL*Base URL of the dev environment to audit (e.g. http://localhost:3000)
TARGET_STAGING_URLBase URL of the staging environment — used by argus_compare for dev vs staging diff. Omit to use CSS analysis mode.
SLACK_BOT_TOKENsecretSlack bot token (xoxb-...) for posting reports. Omit to generate a local report.html instead.
FIGMA_API_TOKENsecretFigma personal access token — enables argus_design_audit to fetch design specs from a Figma frame and compare them against the live DOM (13 fidelity finding types). Omit to skip design fidelity audits.
ARGUS_REDACT_SENSITIVEAegis confidentiality egress boundary. Default ON: every tool response is redacted so secrets, PII, and exploit detail never cross into the calling agent's context (the local on-disk report keeps full fidelity). Set to 0 for byte-identical pre-Aegis output.
Readme
Argus — The QA Layer for AI-Assisted Development
Your AI agent writes the code. Argus checks what it actually built.
One line in your MCP config gives Claude (or any MCP agent) a real Chrome audit engine — 67 audit categories · 149 finding types · zero test files to write or maintain. And with Aegis, what it finds never leaks your secrets to the LLM.
▶ See it in action → argus-qa.com
Details
- Repository
- github.com/ironclawdevs27/argus
- Categories
- Web & Browser Automation, Security & Pentesting
- Package
argusqa-os- Transport
- STDIO
- Auth
- Required
- Registry
- MCP registry, active
Related Web & Browser Automation MCP servers
View all
Pagerunner — The Browser Layer That Learnsenreign/pagerunnerReal Chrome profiles with site intelligence — already logged in, PII anonymization, sessions persist3stars
Anybrowsekc23go/anybrowseConverts any URL to clean, LLM-ready Markdown using real Chrome browsers3stars
anysitedwytmcl/anysite-mcpAny website as MCP tools: a real Chrome signed in as you, and shortcuts the agent saves as tools.1stars
Powershell Mcpimrrd/powershell-mcpHeadless Windows ops over MCP: hidden PowerShell plus in-process SSH, WinRM and SFTP.1stars
Assiststudio Runnerfieldcure/fieldcure-assiststudio-runnerWindows-only headless LLM task automation engine with scheduling via Windows Task Scheduler.1stars
EVM Wallet Signernikicat/mcp-wallet-signerRoute EVM transactions to browser wallets (MetaMask, etc.) for signing via EIP-69631stars