F
licenseNot graded
qualityB
maintenancePassive website security and trust auditor that checks for security, SEO, AI surface, email, and other exposures, producing a score and remediation plan.
-
polaris-audit
by cnohall
Polaris Audit MCP Server
Run website audits directly from Claude, Cursor, or any MCP-compatible AI assistant.
Tools
Tool | Description |
| Submit a URL for a free scan — returns a scan token |
| Poll for results using the token from |
| Fetch a publicly shared report by UUID |
Related MCP server: sitehealth-mcp
Usage with Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"polaris-audit": {
"command": "npx",
"args": ["-y", "@polarisaudit/mcp-server"]
}
}
}Usage with Cursor
Add to .cursor/mcp.json in your project (or ~/.cursor/mcp.json globally):
{
"mcpServers": {
"polaris-audit": {
"command": "npx",
"args": ["-y", "@polarisaudit/mcp-server"]
}
}
}Environment Variables
Variable | Default | Description |
|
| Override the API base URL (useful for self-hosting) |
| (none) | Bearer token for authenticated endpoints |
Example conversation
You: Audit https://example.com for me
Claude: [calls
audit_url] The scan has been submitted. Token:abc123. Let me check when it's ready...[calls
get_scan_resultafter ~45s]Here are the results for example.com:
Overall grade: B (72/100)
Privacy: 65/100 — cookie banner not detected
Security: 80/100
Accessibility: 74/100
Performance: 68/100
3 must-fix issues and 7 quick wins identified.
Development
npm install
npm run build
node dist/index.js # runs the stdio serverAvailable Tools
3 toolsaudit_urlA
Submit a website URL for a free Polaris Audit scan. Returns a scan token you can use with get_scan_result to retrieve the completed report. The scan typically completes within 30–60 seconds.
Inputs: url (required).
get_public_resultA
Fetch a publicly shared Polaris Audit report by its UUID. Returns scores for privacy, security, accessibility, and performance plus a summary of key findings.
Inputs: uuid (required).
get_scan_resultA
Retrieve the results of a previously submitted scan using the scan token returned by audit_url. If the scan is still running, poll again after a few seconds.
Inputs: token (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
A4.2/5.0
Scored across 3 tools
Disambiguation5/5
Each tool has a clearly distinct purpose: audit_url initiates a scan, get_scan_result retrieves results for a submitted scan, and get_public_result fetches publicly shared reports by UUID. There is no overlap in functionality, making tool selection unambiguous for an agent.
Naming Consistency5/5
All tool names follow a consistent verb_noun pattern (audit_url, get_public_result, get_scan_result) using snake_case. The naming is predictable and readable, with no deviations in style or convention.
Tool Count3/5
With only 3 tools, the server feels thin for an audit domain that might benefit from additional operations like listing scans, deleting results, or updating reports. However, the core workflow (submit, retrieve, fetch public) is covered, making it borderline but functional.
Completeness4/5
The tool set covers the essential lifecycle of submitting scans and retrieving results, including public reports. Minor gaps exist, such as no ability to list or manage scans, but agents can work around this by tracking tokens externally.
Related MCP Connectors
AI website audit: security, SEO, performance, UX and accessibility checks with actionable fixes.
Find what to fix on a site, check if changes worked, see how AI reads it. Free audit, no account.
Scan a web page for accessibility, security, privacy, quality and SEO issues, with fixes.
Check a deployed web app for security headers, SEO, accessibility and performance, with a grade.
Related MCP Servers
- AlicenseAqualityCmaintenancePerforms comprehensive website health audits including SSL, DNS, email authentication, performance, uptime, and broken link checks, all without requiring API keys. Returns a scored report with weighted metrics and actionable recommendations.767 npmMIT
- FlicenseNot gradedqualityCmaintenanceAudits any website for SEO issues, providing scored health checks, schema validation, and performance analysis through AI assistants.-
uxlintofficial
AlicenseAqualityBmaintenanceAudits any site's UX the way a design-literate reviewer would — contrast, tap targets, type scale, colour discipline, scan patterns, copy — and returns the rule, the source line and the exact fix.6Apache 2.0