mcp-toolbelt
Online29 DNS, SEO, SSL, security, WHOIS & mail tools for AI agents. Pay per call (x402) or card API key.
What it can do: 39 tools
url_to_markdownread-onlyFetch a URL and return its main text content as clean, readable plain text/markdown-ish output. Strips scripts, styles, and HTML tags.security_headers_auditread-onlyFetch a URL and audit its response headers in one pass: security headers (HSTS, CSP, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, Permissions-Policy) with a score, PLUS its CORS policy (the probe sends a forredirect_chain_checkread-onlyFollow a URL through every HTTP redirect hop and report the full chain, final destination, and issues like redirect loops, too many hops, or HTTPS-to-HTTP downgrades.page_performance_checkread-onlyFetch a URL and measure time-to-first-byte, total fetch time, and response size from this server. Flags missing compression, missing Cache-Control, oversized payloads, and slow TTFB. Lightweight raw-timing check — for Gostructured_data_extractread-onlyFetch a URL and extract structured data deterministically: JSON-LD blocks (each one also VALIDATED — @context/@type presence plus required fields for common schema.org types like Article, Product, Organization, FAQPage),tech_stack_fingerprintread-onlyFetch a URL and fingerprint its likely tech stack from response headers (server, x-powered-by, x-generator) and HTML markers (generator meta tag, framework/CMS-specific script or class patterns). Answers 'what is this siseo_auditread-onlyFetch a URL and run a full on-page SEO audit: title/meta description length, canonical tag, Open Graph + Twitter Card tags, html lang attribute, viewport meta, heading structure, image alt-text coverage, internal/externacheck_robots_sitemapread-onlyCheck a site's robots.txt and sitemap.xml in one call: raw contents (truncated), sitemap presence, an AI-crawler policy analysis (explicit rules for GPTBot, ClaudeBot, CCBot, PerplexityBot, Google-Extended, Bytespider, Abroken_link_checkread-onlyFind broken links two ways. Default (crawl mode): crawl a site starting from a URL (same-origin pages only, bounded by maxPages) and check every linked URL for broken status codes, returning each broken link with the pagai_readiness_auditread-onlyScore how ready a website is for AI agents and LLM-driven discovery, 0-100 with a letter grade: robots.txt presence, explicit AI-crawler policy (GPTBot, ClaudeBot, CCBot, PerplexityBot, and 8 more), llms.txt presence anddomain_health_checkread-onlyCheck a domain's registration expiry (via WHOIS) and DNS health: nameservers, A/AAAA, MX, SPF, and DMARC records. Flags common misconfigurations. WHOIS + DNS only — for the WHOIS record alone use whois_lookup; for delivedns_propagation_checkread-onlyQuery a DNS record for a domain against several major public resolvers (Google, Cloudflare, Quad9, OpenDNS) in parallel and compare the answers. Flags mismatches, which usually mean propagation is still in progress afteremail_deliverability_checkread-onlyDeep-dive email deliverability check for a domain: MX records + reverse-DNS (PTR) on each MX host, common DKIM selector probing, SPF lookup-count (RFC 7208 caps at 10), DMARC policy strength, and DNSBL blacklist lookupswhois_lookupread-onlyLook up a domain's WHOIS registration record: registrar, creation and expiry dates, days remaining, name servers, and domain statuses, direct from the TLD registry. Registration data only — for DNS/mail health as well, udomain_availability_checkread-onlyCheck whether a domain is registered, plus scan common typo-squat variants (adjacent-key substitution, letter omission/doubling, transposition) across popular TLDs (.com, .net, .org, .io, .co, .ai, .app, .dev) for brand-subdomain_discoveryread-onlyEnumerate a domain's subdomains from public Certificate Transparency logs (crt.sh, with a Cert Spotter fallback): every hostname that has ever appeared on a certificate for the domain. Passive reconnaissance - no packetsssl_cert_checkread-onlyConnect to a host over TLS and report its certificate's expiry date, days remaining, issuer, and subject. Fast facts only — for a full graded TLS assessment (protocols, ciphers, vulnerabilities) use ssl_labs_grade insteacheck_open_portsread-onlyTCP-connect scan a host for open ports, plus network intel on the host's resolved IPs (ASN, network owner, BGP prefix, country — via Team Cymru). Defaults to a list of ~20 common service ports (SSH, HTTP/S, mail, DBs, etwebsocket_endpoint_checkread-onlyTest a WebSocket endpoint (ws:// or wss://): attempts the handshake, reports success/failure, time-to-open in ms, and close code/reason. Useful for verifying a WebSocket server is reachable and completes its upgrade handdomain_reportread-onlyBundle: runs seo_audit, domain_health_check (WHOIS + DNS: nameservers, A/AAAA, MX, SPF, DMARC), and email_deliverability_check (DKIM, SPF lookup-count, DMARC strength, DNSBL) against a domain in one call, one charge. Chesafe_browsing_checkread-onlyCheck a URL against Google Safe Browsing's malware/phishing/unwanted-software/PUA blocklists. Requires GOOGLE_SAFE_BROWSING_API_KEY to be configured server-side (free Google Cloud API key).ssl_labs_graderead-onlyFull SSL Labs-style TLS assessment: overall letter grade, protocol support (TLS 1.0-1.3), cipher strength, certificate chain issues, and known vulnerabilities (Heartbleed, POODLE, etc.) for each endpoint. Use this for aexposed_files_checkread-onlyProbe a site for publicly exposed sensitive files attackers scan for: /.env and variants, /.git/config and /.git/HEAD, /.svn/entries, docker-compose files, /.aws/credentials, /.ssh/id_rsa, database dumps (backup.sql, db.pagespeed_insightsread-onlyRun Google's real PageSpeed Insights (Lighthouse + Chrome UX Report) against a URL: performance score, Core Web Vitals (LCP, CLS, INP/TBT), and real-user field data where available. The authoritative, Google-measured scopackage_vulnerability_checkread-onlyLook up a package (optionally pinned to a version) against OSV.dev's aggregated vulnerability database (GitHub Advisories, PyPA, RustSec, Go vuln DB, etc.) for known CVEs/advisories. Supports npm, PyPI, crates.io, RubyGegithub_repo_health_checkread-onlyCheck a GitHub repository's health signals: stars, forks, open issues, license, archived/disabled status, and days since last push. Flags likely-abandoned or unlicensed repos. Useful before depending on a repo.email_address_validateread-onlyValidate a single email address: RFC syntax check, MX record lookup on the domain, disposable/temporary-email-provider detection, and role-account detection (info@, admin@, etc.). Per-address check — different from emailsmtp_server_checkread-onlyLive-probe a mail server over SMTP: connects to port 25 (or a given port), reads the banner, issues EHLO and lists advertised capabilities (STARTTLS, AUTH mechanisms, SIZE, 8BITMIME, PIPELINING), then upgrades via STARTTmcp_server_proberead-onlyProbe a remote MCP server end-to-end: performs the initialize handshake, captures server info and protocol version, lists its tools, and grades tool-quality the way directories like Glama do — description coverage and dewebsite_screenshotRender a URL in a real headless Chromium browser and capture a PNG screenshot — either the viewport or the full scrolling page (capped at 10,000px tall). Options: viewport width/height, device scale factor (retina), waithtml_to_pdfRender a URL or a raw HTML string to a PDF in headless Chromium (print-quality, selectable text). Options: paper format (A4, Letter, Legal, A3, A5, Tabloid), landscape, print backgrounds, margins, and scale. Returns a shphone_validateread-onlyValidate and format a phone number with Google's libphonenumber metadata: valid/possible for its region, E.164, international and national formats, tel: URI, country, and line type (MOBILE, FIXED_LINE, TOLL_FREE, VOIP, …vat_validateread-onlyValidate an EU VAT number against the European Commission's official VIES service: checks the country-specific format first, then asks VIES whether the number is active for intra-EU trade and returns the registered businaddress_normalizeread-onlyNormalize a free-form US postal address to USPS Publication 28 style, deterministically (rule tables, no AI): uppercase, standard street-suffix, directional and unit abbreviations (Street -> ST, Suite -> STE, North -> N)image_resizeDownload an image from a URL and resize it with libvips (sharp): set width and/or height, fit mode (inside keeps aspect ratio within the box, cover crops to fill, contain letterboxes, fill stretches), output format (PNG,csv_to_jsonread-onlyConvert CSV to JSON with a strict RFC 4180 parser: quoted fields, escaped quotes, embedded newlines, CRLF, BOM. Auto-detects the delimiter (comma, semicolon, tab, pipe) or takes one; uses the first row as keys by defaultarchived_page_lookupread-onlyFind the Internet Archive Wayback Machine snapshot of a URL closest to a given date (default: now): capture time, how many days off it is, the viewable snapshot URL, a raw-content URL (original bytes, no Wayback toolbar)favicon_manifest_checkread-onlyCheck a site's browser/OS chrome and PWA metadata: every <link rel=icon> favicon plus /favicon.ico, apple-touch-icon(s), and the web app manifest (fetched and parsed: name, short_name, start_url, display, theme_color, baai_crawler_policy_checkread-onlyReport, per AI crawler, whether a site allows or blocks it: parses robots.txt with RFC 9309 rules (most-specific user-agent group, longest-match Allow/Disallow, * and $ wildcards) for 29 AI agents including GPTBot, ChatG
Connect it
claude mcp add --transport http mcp-toolbelt https://papacasper.com/mcpSettings → Connectors → Add custom connector
URL: https://papacasper.com/mcp{
"mcpServers": {
"mcp-toolbelt": {
"url": "https://papacasper.com/mcp"
}
}
}{
"servers": {
"mcp-toolbelt": {
"type": "http",
"url": "https://papacasper.com/mcp"
}
}
}Questions
What does mcp-toolbelt do?
29 DNS, SEO, SSL, security, WHOIS & mail tools for AI agents. Pay per call (x402) or card API key. It exposes 39 tools to AI assistants.
What tools does mcp-toolbelt provide?
39 tools, including url_to_markdown, security_headers_audit, redirect_chain_check, page_performance_check, structured_data_extract, tech_stack_fingerprint, seo_audit, check_robots_sitemap, broken_link_check, ai_readiness_audit, domain_health_check, dns_propagation_check….
How do I connect mcp-toolbelt to Claude, ChatGPT or Cursor?
Add the remote MCP endpoint https://papacasper.com/mcp as a custom connector or MCP server. Copy-paste setup is on this page.
Does mcp-toolbelt require an account or API key?
No sign-in was needed to list its tools. Individual tools may still need an account or API key.
Is mcp-toolbelt online?
As of 2026-11-19 our probe found it online. It answered 100% of our last 3 checks.
Who publishes mcp-toolbelt?
papacasper.com. The official MCP Registry verified that the publisher controls this domain before accepting the listing.
Similar in Communication
-
BasecampOnline · sign-in requiredOfficialPopularNew
Basecamp's official server: projects, to-dos, cards, messages, docs, schedules, and Campfire.
-
Clutch.coOnlineOfficialPopular
Trusted B2B service providers with verified client reviews
-
Elfsight AI ChatbotOnline · sign-in requiredPopular
Read conversations, leads, knowledge base and analytics of your Elfsight AI Chatbot widgets.
-
HyperFrames by HeyGenOnline · sign-in requiredOfficialNew
Official HyperFrames by HeyGen: the best AI video editor in chat. Captions, motion graphics, MP4.
-
SendPulseOnline · sign-in requiredOfficial
Empower AI agents with SendPulse email, CRM, chatbot, SMTP, and course automation
-
RocketReachOnline · sign-in requiredOfficial
Verified work emails and phones from 700M+ contacts