Argus Testing

An MCP server that tests apps like a real testing engineer—exploring user journeys, discovering unscripted bugs, and proving each finding before reporting it.

Argus is anMCPserver. 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, inspects, verifies persistence, and records reproducible bugs. Every certified finding isindependently re-confirmed from a clean page loadbefore it's reported.

Product page·Quick start·Why Argus·Compared·Tools·Benchmarks

flowchart LR A(["observe"]) --> B{"looks wrong?"} B -->|not sure| C["act: click · type · resize · verify"] C --> A B -->|bug| D["verify_persistence — reload from a clean state"] D -->|symptom repeats| E(["VERIFIED"]) D -->|symptom gone| F(["dropped — no false positive"]) E --> G[["report: HTML · JSON · JUnit · SARIF"]]

The agent is the intelligence. Argus supplies concise QA guidance, a description-keyed tool surface (click_what("Login button"), notclick(7)), a goal coverage ledger, and areproduction-receipt enginethat turns "the model thinks this is a bug" into "this bug is real, here's the proof."

Withuvinstalled, no global Python package install is required. Install Chromium once:

uvx --from playwright playwright install chromium

claude mcp add argus -- uvx --from argus-testing argus-mcp

codex mcp add argus -- uvx --from argus-testing argus-mcp

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

The defaultcoreprofile exposes the primary web-testing workflow without flooding the host with every specialist tool. Useuvx --from argus-testing argus-mcp --list-toolsto inspect the selected profile,--tool-profile screenfor native macOS testing, or--tool-profile fullfor the entire advanced surface.ARGUS_TOOL_PROFILEprovides the same setting through the environment.

"Test my app athttp://localhost:3000— find real bugs."

pip install argus-testing playwright install chromium claude mcp add argus -- argus-mcp

# Uses a LiteLLM-backed planner. Set a provider key (OPENAI_API_KEY, DEEPSEEK_API_KEY, …). uvx --from argus-testing argus http://localhost:3000 --model deepseek/deepseek-chat # Higher recall: union N independent passes (deduped, proven instance kept) uvx --from argus-testing argus http://localhost:3000 --passes 3

pip install 'argus-testing[mac]' brew install cliclick # keystroke / coordinate fallback argus-mcp --doctor # check Screen Recording + Accessibility grants claude mcp add argus-screen -- argus-mcp --tool-profile screen

Same description-keyed tools, but the target is whatever app is foreground on macOS — Notes, Cursor, Safari, your in-progress feature. No headless Chrome, no scripted Playwright. Argus sees what you see, via the Accessibility tree.

Argus writes each run's screenshots into its own run directory so later tests cannot overwrite earlier evidence. Long browser sessions also keep bounded in-memory event logs and only read response bodies for inspectable API traffic; binary and oversized bodies are skipped before they enter Python memory.

Report cleanup is explicit and dry-run by default. The newest 20 complete runs are protected in this example;.argusjournals and state capsules are never deleted:

argus-cleanup --output ./argus-reports --keep-runs 20 argus-cleanup --output ./argus-reports --keep-runs 20 --apply

Use--older-than-daysand--max-size-mbfor stricter policies. Advanced limits can be adjusted withARGUS_MAX_NETWORK_EVENTS,ARGUS_MAX_ERROR_EVENTS,ARGUS_MAX_DOWNLOAD_EVENTS,ARGUS_MAX_DIALOG_EVENTS,ARGUS_MAX_RESPONSE_BODY_BYTES, andARGUS_MAX_RESPONSE_READ_BYTES. Responses without a declared length are skipped by default;ARGUS_CAPTURE_UNKNOWN_LENGTH_BODY=1opts into reading them. When a limit discards old evidence, Argus says so in tool output and the final session summary.

Existing testing tools only test what you script.Playwright and Cypress run the assertions you wrote. Argusdiscoversbugs you didn't think to test for — and then does the thing an LLM alone can't be trusted to do:proves them.

On the axis that matters for finding bugs —autonomously discover, independently verify, and report— Argus occupies a different slot from the browser-MCP crowd:

These aren't "worse" tools — they're a different job. Playwright MCP gives an agent excellent hands; Chrome DevTools MCP gives it deep network/perf/memory inspection Argus doesn't have. Argus is the layer thatdecides what's a bug and proves it.Use them together.

$ python -m argus.bench --target all buggytasks 22 / 22 = 100 % · mechanical bugs (console errors, fake delete, auth bypass…) darkshop 12 / 12 = 100 % · human-eye bugs (fake scarcity, lying toasts, stale state…) ────────────────────────────────────────────────────────────────────── total 34 / 34 = 100 % · reproducible from git clone in two commands

34 / 34is thecapability ceiling— what'sfindablethrough the tool surface, measured by deterministic scripts. It is deliberately separate fromhow often a given LLM remembers to use the tools well, which is noisy and honestly reported below.

python -m argus.bench.agent_runnerputs anactual modelin the driver's seat and scores recall across trials. What we've learned running it:
- Real recall sits well below the34/34ceiling.A live driver finds a fraction of the seeded bugs per pass — the ceiling is what'sfindable, this is what a modelfinds.
- Variance is large — never rank models on a few runs.Per-trial recall swings widely; we report the spread, not a single hero number.
- Dogfooding the bench found real bugs in Argus itself— arecord_bugcrash on a string argument that silently dropped findings, resolver misses on common phrasings. The tool-testing tool got tested.
- Precision holds regardless of driver.Across every trial, the reproduction receipt kept false-certifications at zero — a weak model finds fewer bugs, but the ones marked VERIFIED are still real.

BuggyTasks(:5555) — 22 mechanical bugs in a task app: console errors, dead links, fake delete (UI says "deleted!" but data persists on refresh), auth bypass, NaN dates, off-by-one counts, race conditions. The "scripted E2E could find these" tier.

python test-site/app.py # BuggyTasks :5555 python human-eye-fixture/app.py # DarkShop :5556 python -m argus.bench --target all

argus-mcpstarts with the focusedcoreweb profile. Every public tool is documented below. The counts are also available directly from the installed server:

uvx --from argus-testing argus-mcp --list-tools uvx --from argus-testing argus-mcp --tool-profile screen --list-tools uvx --from argus-testing argus-mcp --tool-profile full --list-tools

Reports keep original screenshots as evidence and, by default, write compact WebP previews underreport-assets/instead of base64-embedding every full-size PNG into the HTML. SetARGUS_PORTABLE_REPORT=1when a single self-contained HTML file is more important than size. JSON output includes complete reproduction receipts, the coverage contract and its structured evidence references, constraints, review mode, tool-call and recorded-step counts, screenshot metadata, and qualitative observations. JUnit suite failure totals match the emitted<failure>nodes.

Safety:per-call timeout, a 30-minute session cap, a~/.argus/abortpanic file that halts every subsequent action, and an automatic before/after screenshot trail on every action.

The full profile includes every core and screen tool above plus these 36 specialist tools. Use it when the workflow genuinely needs low-level state, fault injection, multi-tab control, coordinates, or crawling.

To exposeeval_jsas an operational tool rather than a disabled safety stub:

uvx --from argus-testing argus-mcp --tool-profile full --unsafe

Argus runs on your machine and does not send telemetry to an Argus-operated service. Reports and screenshots stay under./argus-reportsby default; your MCP host and its configured model provider can still receive tool results included in the conversation. Browser actions and native macOS controls can cause real side effects, so use test accounts and non-production data wherever possible.

Read the fullprivacy disclosureandsecurity policybefore using Argus against sensitive systems.

argus/ ├── mcp_server.py # tool surface + role instructions + reproduction-receipt engine ├── browser.py # Playwright backend: DOM/ARIA extraction, capsule/replay ├── resolver.py # description → element (web + screen) ├── reporter.py # HTML + JSON + JUnit + SARIF ├── detector.py # console + network capture (only) ├── cli.py # argus (explore) + argus-regression ├── bench/ # deterministic ceiling + real-LLM recall harness └── screen/ # macOS AX backend, permissions, safety test-site/ # BuggyTasks (22 mechanical bugs) human-eye-fixture/ # DarkShop (12 human-eye bugs)

MIT licensed·Product page·Agent install guide·Privacy·Security· Built byYichen Wu

Create and manage end-to-end tests using the Octomind platform.