Penthera
Offline, rule-based security checks for your repo, dependencies, AI agent config and local app.
Description from the maker (original English)
SEO, performance, and security audits for any URL — no API keys required
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"siteaudit": {
"command": "uvx",
"args": [
"siteaudit-mcp"
]
}
}
}Run this in your terminal
claude mcp add siteaudit -- uvx siteaudit-mcpPaste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"siteaudit": {
"command": "uvx",
"args": [
"siteaudit-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"siteaudit": {
"type": "stdio",
"command": "uvx",
"args": [
"siteaudit-mcp"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 9, 2026
The registry name was verified with the GitHub account vdalhambra, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.2.0) reached the registry 7 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Python (uv) on your computer.
In the same category: Penthera, Draugr, Harbor
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Offline, rule-based security checks for your repo, dependencies, AI agent config and local app.
Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
Read-only access to Harbor: projects, artifacts, vulnerabilities, robots, replication, agent skills.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Instant SEO, Performance, and Security Audits for AI Agents — analyze any URL with a single tool call via the Model Context Protocol (MCP).
SiteAudit is an MCP server that gives Claude Code, Cursor, Windsurf, and any AI agent the ability to audit any website instantly. No API keys, no configuration, no cost. The complete website audit toolkit for AI-powered development.
Try it now — no install needed: Open SiteAudit in the MCPize Playground — runs in your browser, free tier (100 audits/month)
Here are concrete examples of what you can ask your AI agent once SiteAudit is installed:
| Feature | SiteAudit MCP | Ahrefs | Screaming Frog | Google Lighthouse |
|---|---|---|---|---|
| Works with Claude Code / Cursor | Yes | No | No | CLI only |
| No API key needed | Yes | No ($99/mo) | Free (limited) | Yes |
| SEO + Security + Performance | All three | SEO only | SEO only | Performance only |
| AI-native (MCP protocol) | Yes | REST API | Desktop app | CLI / API |
| Broken link checker | Yes | Yes | Yes | No |
| Lighthouse integration | Yes | No | No | It is Lighthouse |
| Multi-site comparison | Yes | Manual | Manual | Manual |
| Free | Yes | $99+/mo | Free (500 URLs) | Yes |
| Tool | Description |
|---|---|
full_audit | Comprehensive SEO + performance + security audit with unified score (0-100) |
seo_audit | SEO analysis: title, meta, headings, images, links, structured data, Open Graph |
security_audit | Security headers, HTTPS, HSTS, CSP, SSL certificate check, cookie flags |
performance_audit | Response time, page size, compression, caching, redirects |
compare_sites | Side-by-side comparison of multiple websites |
lighthouse_audit | Google PageSpeed Insights: performance, accessibility, best practices, SEO |
check_links | Crawl and validate all links on a page — find broken links, redirects, timeouts |
check_robots_txt | Parse and analyze robots.txt rules, directives, and sitemaps |
The fastest way to get started. No terminal, no config files, no Python setup — works in any MCP client:
👉 [Install SiteAudit on MCPize](https://mcpize.com/mcp/siteaudit-mcp) — Free tier available (100 audits/month)
Or add to your MCP config directly:
{
"mcpServers": { "siteaudit": { "url": "https://siteaudit-mcp.mcpize.run/mcp" } } }
Why MCPize?
See pricing below for all tiers including Agency and Enterprise.
For those who prefer to run the server locally:
Claude Code CLI
claude mcp add siteaudit -- uvx --from siteaudit-mcp siteaudit
Claude Desktop / Cursor / Windsurf (local)
{
"mcpServers": { "siteaudit": { "command": "uvx", "args": ["--from", "siteaudit-mcp", "siteaudit"] } } }
</details>
From PyPI
pip install siteaudit-mcp
siteaudit
</details>
From source
git clone https://github.com/vdalhambra/siteaudit-mcp.git
cd siteaudit-mcp uv sync uv run siteaudit
</details>
Smithery
npx -y @smithery/cli install @vdalhambra/siteaudit --client claude
Note: Self-hosted = full feature access but you manage updates, uptime, and Google PageSpeed quotas. For most users, MCPize is the better choice.
| Tier | Price | Audits/month | Includes |
|---|---|---|---|
| Free | $0 | 100 | Basic audit (no Lighthouse) |
| Hobby | $7/mo | 2,500 | Full audit without site comparison |
| Pro ⭐ | $19/mo | 10,000 | All 8 tools + full Lighthouse + priority |
| Agency | $49/mo | 50,000 | Pro + 10 saved sites + scheduled audits |
| Agency Plus | $119/mo | 200,000 | Agency + white-label PDF reports + 25 seats |
| Enterprise | $349/mo | Unlimited | Agency Plus + on-prem + custom integrations + SLA |
Annual plans: Get 2 months free (pay for 10, use 12).
Bundle: Combine with FinanceKit MCP for $39/mo (Pro Combo — save 19%).
👉 [View all pricing on MCPize](https://mcpize.com/mcp/siteaudit-mcp)
URL: https://github.com
Overall Score: 90/100 (Grade: A)
Scores: SEO: 85/100 Performance: 95/100 Security: 90/100
Issues: 0 Warnings: 3 [SEO] No JSON-LD structured data [Security] Missing Content-Security-Policy header [Security] Server header discloses: 'GitHub.com'
SiteAudit works entirely by analyzing the HTML and HTTP headers of the target URL. No third-party API keys needed. It uses:
requests for HTTP fetchingBeautifulSoup for HTML parsingssl for certificate checkingSiteAudit works with any AI agent or IDE that supports the Model Context Protocol:
claude mcp addclaude_desktop_config.json.cursor/mcp.jsonIf SiteAudit is useful to you, please consider supporting ongoing development:
MIT