PageGuard MCP server
io.github.pageguard/pageguard-mcp·v1.0.1·1 starsPrivacy compliance scanning for AI coding tools. Detects tracking tech, cookies, and data gaps.
1 stars45 downloads/wk
Reviews
Write oneNobody has reviewed PageGuard MCP yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
PageGuard MCP tools (3)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
pageguard_generate_docsGenerate AI-written legal compliance documents (privacy policy, terms of service, cookie policy, etc.) for a previously scanned site. Requires a scanId from a prior URL scan and a PAGEGUARD_API_KEY with available credits. Document types: 'single' ($29 — privacy + terms + cookie), 'bundle' ($49 — everything), 'addon_security' ($19), 'addon_a11y' ($19), 'addon_schema' ($19), 'app_bundle' ($39), 'sub
pageguard_scan_localScan a local project directory for privacy-relevant technologies by checking package.json dependencies, config files, and .env files against known tracking/analytics signatures. No API key or network access needed. Returns a ComplianceReport with detected technologies, data types collected, cookies, and third-party processors.
pageguard_scan_urlScan a live website URL for privacy compliance issues. Detects tracking technologies, cookies, third-party data collection, and compliance gaps by analyzing the actual deployed site. Returns a ComplianceReport with risk score, detected technologies, and compliance gaps. Optionally uses PAGEGUARD_API_KEY env var for authenticated requests.
Public scan report
scanner v0.1.9 · 2026-09-27 · same rubric, same numbers if you re-run it
- Code scan4 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 174 days ago8/15
- Maintainer identityregistry namespace matches repository owner7/10
How PageGuard MCP compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 71/100
- higher than 36% of 48,255 servers
- Tools
- 3
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 1
- more than 65% of 28,688 servers
- Downloads a week
- 45
- more than 37% of 12,191 servers with a package
What its tools let an agent do: 3 read
Install PageGuard MCP in Claude Code, Cursor or VS Code
Runs npx -y pageguard-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add pageguard-mcp -- npx -y pageguard-mcp
What the publisher says
From the PageGuard MCP repository's README, as published. We do not edit it. Read it on GitHub
pageguard-mcp
MCP (Model Context Protocol) server that exposes PageGuard privacy compliance scanning as tools for AI coding assistants. Works with Claude Code, Cursor, Windsurf, ChatGPT, and any MCP-compatible environment.
What it does
- Local scan — Detects tracking technologies, cookies, and third-party data collection from your project's package.json, config files, and .env files. No API key needed, no network requests.
- URL scan — Scans a live website for privacy compliance issues including risk scoring and compliance gap analysis.
- Document generation — Generates AI-written legal documents (privacy policy, terms of service, cookie policy, etc.) tailored to your detected technologies.
Installation
Claude Code
Add to your project's .mcp.json or global MCP config:
{
"mcpServers": {
"pageguard": {
"command": "npx",
"args": ["pageguard-mcp"]
}
}
}Cursor
Add to Cursor Settings > MCP Servers:
{
"mcpServers": {
"pageguard": {
"command": "npx",
"args": ["pageguard-mcp"]
}
}
}Windsurf
Add to your MCP configuration:
{
"mcpServers": {
"pageguard": {
"command": "npx",
"args": ["pageguard-mcp"]
}
}
}Environment variables
Tools
pageguardscanlocal
Scan a local project directory for privacy-relevant technologies.
Input:
- path (optional) — Absolute path to project directory. Defaults to current working directory.
Output: ComplianceReport JSON with detected technologies, data types, cookies, and third-party processors.
pageguardscanurl
Scan a live website URL for privacy compliance issues.
Input:
- url (required) — Full URL to scan, e.g. https://example.com
Output: ComplianceReport JSON with risk score, detected technologies, and compliance gaps.
pageguardgeneratedocs
Generate AI-written legal compliance documents for a scanned site.
Input:
- scanId (required) — Scan ID from a prior pageguardscanurl result
- documentType (optional) — One of: single ($29), bundle ($49), addonsecurity ($19), addona11y ($19), addonschema ($19), appbundle ($39), submission_guide ($19). Defaults to bundle.
Output: Generated document content.
Pricing
Scanning is free. Document generation requires credits:
- Privacy Docs ($29) — Privacy Policy + Terms of Service + Cookie Policy
- Fix Everything ($49) — All docs + Security Guide + Accessibility Report + Schema Markup
- App Bundle ($39) — Privacy docs + App Store Submission Guide
- Add-ons ($19 each) — Security Guide, Accessibility Report, Schema Markup, Submission Guide
- Bulk packs — 5 for $79, 15 for $149, 50 for $349
Get an API key at getpageguard.com/#pricing.
License
MIT
Nothing above is checked by us. What we check is on the safety report.
PageGuard MCP: common questions
- Is PageGuard MCP server safe?
- Mostly: it is graded B (71/100). Read the PageGuard MCP safety report
- How do I install PageGuard MCP?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does PageGuard MCP need an API key?
- Yes. The registry entry asks for
PAGEGUARD_API_KEY. - Is PageGuard MCP maintained?
- The last commit was 211 days ago (2026-04-07). The latest release is v1.0.1.
- How does PageGuard MCP compare with other MCP servers?
- safety score 71/100 (higher than 36% of 48,255 servers); tools 3 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.