CCM
/MCP
SkillsMCPMarketplacesDigestToolsAdvertise

This week in Claude

Every Monday: Claude Code, Agent SDK, MCP, and the Anthropic platform moves worth your time.

Skills by Category
Frontend DevelopmentBackend & APIsTesting & QASecurityDevOps & CI/CDGit & Pull RequestsDocumentationCode Review & QualityAI & Agent BuildingSkill Development
MCP Servers by Category
Sales & MarketingWeb & Browser AutomationDatabasesAI & LLM ToolsCloud & InfrastructureCommunication & MessagingDeveloper ToolsDesign & CreativeDocuments & KnowledgeSearch & Web Crawling
Marketplaces by Category
AI Agents & OrchestrationLLM IntegrationDevelopment ToolsFrontend & UIBackend & APIsDatabasesTesting & Code QualityDevOps & CloudSecurity & ComplianceGit & Version Control

Claude Code Marketplaces

Discover Claude Code plugins, extensions, and tools. Automatically updated directory of Anthropic Claude AI marketplaces with development tools, productivity plugins, and integrations.

Resources

  • Browse Skills
  • Browse MCP Servers
  • Browse Marketplaces
  • Skill index
  • MCP index
  • Marketplace index
  • Plugins Reference

Community

  • About
  • Tools
  • Feedback
  • Privacy Policy
  • Advertise

Built for the Claude Code community with Claude Code by mertbuilds.com

Independent project, not affiliated with Anthropic
vdalhambra avatar

Siteaudit Mcp

vdalhambra/siteaudit-mcp
3STDIOregistry active
Summary

Gives Claude the ability to audit any website's SEO, security, and performance without API keys or configuration. You get eight tools including full_audit for comprehensive scoring, seo_audit for meta tags and structured data analysis, security_audit for HTTPS and CSP headers, lighthouse_audit via Google PageSpeed Insights, and check_links for broken link detection. Useful when you're comparing competitor sites, troubleshooting production security headers, or getting actionable SEO recommendations without leaving your editor. The self-hosted version runs via uvx from PyPI, or you can use the MCPize hosted endpoint to skip local setup entirely. Returns structured scores, specific warnings, and prioritized fixes rather than raw data dumps.

CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →

PyPI version License: MIT Python 3.11+ Glama MCP Server

SiteAudit MCP

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)

Use Cases

Here are concrete examples of what you can ask your AI agent once SiteAudit is installed:

  • "Audit example.com and give me a prioritized list of SEO fixes" — Full SEO audit with title tags, meta descriptions, headings, structured data, Open Graph, and actionable recommendations
  • "Check the security headers on my production site" — HTTPS, HSTS, CSP, X-Frame-Options, cookie flags, SSL certificate validity, and server disclosure
  • "Compare my site vs 3 competitors side-by-side" — Multi-site comparison with scores for SEO, performance, and security across all sites
  • "Run a Lighthouse audit on my homepage" — Google PageSpeed Insights performance, accessibility, best practices, and SEO scores
  • "Find all broken links on my site" — Crawl internal and external links, report 404s, redirects, and unreachable URLs
  • "Check if my robots.txt is blocking anything important" — Parse robots.txt rules, find sitemap references, and identify potential crawl issues

Why SiteAudit?

FeatureSiteAudit MCPAhrefsScreaming FrogGoogle Lighthouse
Works with Claude Code / CursorYesNoNoCLI only
No API key neededYesNo ($99/mo)Free (limited)Yes
SEO + Security + PerformanceAll threeSEO onlySEO onlyPerformance only
AI-native (MCP protocol)YesREST APIDesktop appCLI / API
Broken link checkerYesYesYesNo
Lighthouse integrationYesNoNoIt is Lighthouse
Multi-site comparisonYesManualManualManual
FreeYes$99+/moFree (500 URLs)Yes

Tools (8)

ToolDescription
full_auditComprehensive SEO + performance + security audit with unified score (0-100)
seo_auditSEO analysis: title, meta, headings, images, links, structured data, Open Graph
security_auditSecurity headers, HTTPS, HSTS, CSP, SSL certificate check, cookie flags
performance_auditResponse time, page size, compression, caching, redirects
compare_sitesSide-by-side comparison of multiple websites
lighthouse_auditGoogle PageSpeed Insights: performance, accessibility, best practices, SEO
check_linksCrawl and validate all links on a page — find broken links, redirects, timeouts
check_robots_txtParse and analyze robots.txt rules, directives, and sitemaps

Installation

⭐ Recommended: MCPize (hosted, no setup)

The fastest way to get started. No terminal, no config files, no Python setup — works in any MCP client:

👉 Install SiteAudit on MCPize — Free tier available (100 audits/month)

Or add to your MCP config directly:

{
  "mcpServers": {
    "siteaudit": {
      "url": "https://siteaudit-mcp.mcpize.run/mcp"
    }
  }
}

Why MCPize?

  • ✅ Zero setup — works immediately in Claude Desktop, Cursor, Windsurf, Claude Code
  • ✅ Always up-to-date — new SEO checks and features added continuously
  • ✅ Scales with you — upgrade to Pro ($19/mo) for 10,000 audits + full Lighthouse + priority
  • ✅ No rate limits on PageSpeed API — we handle the Google quota for you
  • ✅ Reliable uptime — managed cloud infrastructure

See pricing below for all tiers including Agency and Enterprise.


💻 Advanced: Self-hosted (developers)

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"]
    }
  }
}
From PyPI
pip install siteaudit-mcp
siteaudit
From source
git clone https://github.com/vdalhambra/siteaudit-mcp.git
cd siteaudit-mcp
uv sync
uv run siteaudit
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.


Pricing

TierPriceAudits/monthIncludes
Free$0100Basic audit (no Lighthouse)
Hobby$7/mo2,500Full audit without site comparison
Pro ⭐$19/mo10,000All 8 tools + full Lighthouse + priority
Agency$49/mo50,000Pro + 10 saved sites + scheduled audits
Agency Plus$119/mo200,000Agency + white-label PDF reports + 25 seats
Enterprise$349/moUnlimitedAgency 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

What it checks

SEO Audit (20+ checks)

  • Title tag (presence, length optimization)
  • Meta description (presence, length)
  • H1 tag (count, content)
  • Heading hierarchy (H1-H6)
  • Image alt text coverage
  • Internal/external link count
  • Canonical URL
  • Open Graph tags
  • Twitter Card tags
  • Mobile viewport
  • Structured data (JSON-LD)
  • Favicon
  • Language attribute
  • robots meta directives
  • Content length (word count)

Security Audit (10+ checks)

  • HTTPS enforcement
  • HSTS header (with subdomains and preload)
  • Content-Security-Policy
  • X-Content-Type-Options
  • X-Frame-Options
  • Referrer-Policy
  • Permissions-Policy
  • Server/X-Powered-By disclosure
  • Cookie security flags (Secure, HttpOnly, SameSite)
  • SSL certificate validity and expiration

Performance Audit

  • Server response time (ms)
  • Page size (KB)
  • Compression (gzip/brotli)
  • Cache-Control headers
  • Redirect chain analysis
  • HTTP status code

Lighthouse Audit (via Google PageSpeed Insights)

  • Performance score
  • Accessibility score
  • Best practices score
  • SEO score
  • Core Web Vitals (FCP, LCP, TBT, CLS)

Example Output

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'

No API Keys Required

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 fetching
  • BeautifulSoup for HTML parsing
  • Python ssl for certificate checking
  • Google PageSpeed Insights API (free, no key required for basic usage)

Compatible AI Agents

SiteAudit works with any AI agent or IDE that supports the Model Context Protocol:

  • Claude Code (CLI) — claude mcp add
  • Claude Desktop — claude_desktop_config.json
  • Cursor — .cursor/mcp.json
  • Windsurf — MCP settings
  • Copilot — MCP configuration
  • Any MCP client — stdio or HTTP transport

Support this project

If SiteAudit is useful to you, please consider supporting ongoing development:

  • 💎 Upgrade to Pro on MCPize — Best way to support + get priority access
  • ⭐ Star this repo — Helps other developers find it
  • 💖 Sponsor on GitHub — One-time or recurring support
  • 🐦 Share on Twitter/X — Tag @ElAgenteRayo

License

MIT

Featured
CodeRabbit
CodeRabbit
AI writes the code. CodeRabbit catches the slop.
Try For Free →
inference shell
inference shell
create and run specialised agents in minutes
build now →
MCP-ready Email SendingMCP-ready Email Sending
MCP-ready Email Sending
Plug Mailtrap into your AI workflow and let it handle the email.
Connect Mailtrap MCP →
Make your agent a DeFi expert
Make your agent a DeFi expert
Agent, run crypto. Access onchain data & trade routes via 1inch.
Install now →
Capacitor - Shared memory for your team’s coding agents.
Capacitor - Shared memory for your team’s coding agents.
Make coding agent sessions - Searchable, Shareable, Vendor-neutral & Scored.
Try For Free →
CodeScene MCP ServerCodeScene MCP Server
CodeScene MCP Server
Your agent targets a perfect 10 Code Health score. Deterministic. Every commit.
Try For Free →
Give your AI the whole web as clean markdownGive your AI the whole web as clean markdown
Give your AI the whole web as clean markdown
Integrate web data into your AI product. One API to scrape website & brand data.
Get API Key Now →
belt - the only tool your agent needs
belt - the only tool your agent needs
belt cli automatically finds the best tools and skills for your agent. image, video, music, tts...
one prompt install →
Categories
Security & Pentesting
Registryactive
Packagesiteaudit-mcp
TransportSTDIO
UpdatedApr 14, 2026
View on GitHub

More from vdalhambra

  • Financekit Mcp4

Related Security & Pentesting MCP Servers

View all →
cinderfi avatar
Cinderfi — Retirement Planning

com.cinderfi/retirement-planning

Retirement planning for Canada & US. CPP/OAS, Social Security, RRSP/TFSA, 401k/IRA, Monte Carlo.
2
goklab avatar
Guardvibe

goklab/guardvibe

Deterministic security layer your AI can't be. 442 rules, 37 tools, CLI + doctor + host audit.
2
downatthebottomofthemolehole avatar
Megalinter

io.github.downatthebottomofthemolehole/megalinter

MCP server for running Ox Security MegaLinter via mega-linter-runner
2
figuard avatar
Figuard Mcp

io.github.figuard/figuard-mcp

Pre-flight spend authorization for AI agents. Set a budget, enforce limits, audit every decision.
2
inkog-io avatar
Inkog

io.github.inkog-io/inkog

Security co-pilot for AI agents. Scan for vulnerabilities, audit MCP servers, verify governance.
2
wiserautomation avatar
Suprawall Mcp

io.github.wiserautomation/suprawall-mcp

SupraWall security gateway for AI agents. Provides deterministic guardrails for MCP agents.
2