argus-qa
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Server port (default: 3001). | 3001 |
| GITHUB_SHA | No | Commit SHA for the commit status check — injected automatically by GitHub Actions. | |
| GITHUB_TOKEN | No | GitHub personal access token — required for PR comment + commit status integration. | |
| ARGUS_ENV_FILE | No | Path to your app's .env file — C1 cross-references env vars used in source code against this file to detect missing declarations. | |
| TARGET_DEV_URL | Yes | Base URL of your dev environment. | |
| ARGUS_LOG_LEVEL | No | Pino log level — trace, debug, info, warn, error, fatal (default: info). | info |
| SLACK_BOT_TOKEN | No | xoxb-... Bot User OAuth Token. Omit to enable Slack-optional mode — Argus generates report.html and opens it in the browser instead. | |
| ARGUS_LOG_PRETTY | No | Set to 1 for human-readable log output instead of JSON (dev mode). | |
| ARGUS_REPORT_URL | No | Full URL to the hosted HTML report — linked from the GitHub commit status check. | |
| ARGUS_SOURCE_DIR | No | Path to your app's source directory — enables codebase cross-reference. | |
| GITHUB_PR_NUMBER | No | PR number for comment targeting — set via ${{ github.event.pull_request.number }} in your workflow. | |
| ARGUS_CONCURRENCY | No | Number of parallel MCP clients for route crawling (default: 1 = sequential). | 1 |
| GITHUB_REPOSITORY | No | Repository in owner/repo format — required for GitHub PR integration. | |
| REPORT_OUTPUT_DIR | No | Where to write reports (default: ./reports). | ./reports |
| ARGUS_OTEL_CONSOLE | No | Set to 1 to print OTel spans to stdout without an OTLP endpoint (dev tracing). | |
| TARGET_STAGING_URL | No | Base URL of staging. If blank → CSS analysis mode. | |
| ARGUS_RETRY_ATTEMPTS | No | Max retry attempts for navigate/fill MCP calls (default: 3). | 3 |
| SLACK_CHANNEL_DIGEST | No | Channel ID for info / daily digest (required when Slack is configured). | |
| SLACK_SIGNING_SECRET | No | Verifies slash command / interaction requests from Slack (required only when using /argus-retest). | |
| SLACK_CHANNEL_CRITICAL | No | Channel ID for critical bugs (required when Slack is configured). | |
| SLACK_CHANNEL_WARNINGS | No | Channel ID for warnings (required when Slack is configured). | |
| ARGUS_WATCH_INTERVAL_MS | No | Watch mode poll interval in milliseconds (default: 3000). | 3000 |
| SCREENSHOT_DIFF_THRESHOLD | No | Pixel diff % to flag (default: 0.5). | 0.5 |
| OTEL_EXPORTER_OTLP_ENDPOINT | No | OTLP collector endpoint — enables span/metric export to Jaeger, Grafana Tempo, Datadog, etc. |
Capabilities
Features and capabilities supported by this server
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| argus_auditB | Run a quick (cheap) QA pass on a URL. Returns findings as JSON. |
| argus_audit_fullA | Run a deep QA pass on a URL using all analyzers — Lighthouse performance/accessibility scoring, responsive layout checks across mobile/tablet/desktop viewports, memory leak detection via heap snapshot, hover-state bug detection, and accessibility tree snapshot. Returns a full JSON report with findings grouped by severity. |
| argus_compareA | Snapshot and diff two environments (dev vs staging) side-by-side. Navigates both URLs, captures screenshots, runs the full analyzer suite on each, then diffs the findings to surface regressions — things that appear in staging but not dev, or changed severity. Configure the two target URLs via TARGET_DEV_URL and TARGET_STAGING_URL environment variables before starting the server. |
| argus_last_reportA | Return the most recent Argus JSON report from the reports/ directory. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ironclawdevs27/Argus'
If you have feedback or need assistance with the MCP directory API, please join our Discord server