mcp-toolbelt
REMOTE · PAPACASPER.COM
29 DNS, SEO, SSL, security, WHOIS & mail tools for AI agents. Pay per call (x402) or card API key.
Available components
Last scanned (19 hours ago)
Scores higher than 84% of remote servers
Reachable. Last reached 21 Nov 2026.
Category Security
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability72
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 6021 tokens (~154/item across 39 items; 39 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management100
- No destabilizing schema changes in the last 30 days.Pass
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 39 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 40 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities20
- Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28. See how to fix → Fail
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Nov 26 +2
- Stability: fail → pass ▲ security
- 18 Nov 26 +7
- Authorization: unverified → partial ▲ security
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: 125 → 154 ▼ functional
- Server version: 1.3.1 → 1.4.0 functional
- New tool “address_normalize” functional
- New tool “ai_crawler_policy_check” functional
- New tool “archived_page_lookup” functional
- New tool “csv_to_json” functional
- New tool “favicon_manifest_check” functional
- New tool “html_to_pdf” functional
- New tool “image_resize” functional
- New tool “phone_validate” functional
- New tool “vat_validate” functional
- New tool “website_screenshot” functional
- Tool “ai_readiness_audit” changed its title: AI Readiness Audit cosmetic
- Tool “broken_link_check” changed its title: Broken Link Check cosmetic
- Tool “check_open_ports” changed its title: Check Open Ports cosmetic
- Tool “check_robots_sitemap” changed its title: Robots and Sitemap Check cosmetic
- Tool “dns_propagation_check” changed its title: DNS Propagation Check cosmetic
- Tool “domain_availability_check” changed its title: Domain Availability Check cosmetic
- Tool “domain_health_check” changed its title: Domain Health Check cosmetic
- Tool “domain_report” changed its title: Domain Report cosmetic
- Tool “email_address_validate” changed its title: Email Address Validate cosmetic
- Tool “email_deliverability_check” changed its title: Email Deliverability Check cosmetic
- Tool “exposed_files_check” changed its title: Exposed Files Check cosmetic
- Tool “github_repo_health_check” changed its title: GitHub Repo Health Check cosmetic
- Tool “mcp_server_probe” changed its title: MCP Server Probe cosmetic
- Tool “package_vulnerability_check” changed its title: Package Vulnerability Check cosmetic
- Tool “page_performance_check” changed its title: Page Performance Check cosmetic
- Tool “pagespeed_insights” changed its title: PageSpeed Insights cosmetic
- Tool “redirect_chain_check” changed its title: Redirect Chain Check cosmetic
- Tool “safe_browsing_check” changed its title: Safe Browsing Check cosmetic
- Tool “security_headers_audit” changed its title: Security Headers Audit cosmetic
- Tool “seo_audit” changed its title: SEO Audit cosmetic
- Tool “smtp_server_check” changed its title: SMTP Server Check cosmetic
- Tool “ssl_cert_check” changed its title: SSL Certificate Check cosmetic
- Tool “ssl_labs_grade” changed its title: SSL Labs Grade cosmetic
- Tool “structured_data_extract” changed its title: Structured Data Extract cosmetic
- Tool “subdomain_discovery” changed its title: Subdomain Discovery cosmetic
- Tool “tech_stack_fingerprint” changed its title: Tech Stack Fingerprint cosmetic
- Tool “url_to_markdown” changed its title: URL to Markdown cosmetic
- Tool “websocket_endpoint_check” changed its title: WebSocket Endpoint Check cosmetic
- Tool “whois_lookup” changed its title: WHOIS Lookup cosmetic
- 11 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 76 to 79.
- 10 Nov 26 −1
No change was recorded against any check on this day. Stability & Change Management went from 79 to 76.
- 6 Nov 26 0
- We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
- 31 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Server version: 1.0.0 → 1.3.1 functional
- 21 Oct 26 0
- Stability: pass → fail ▼ security
- A breaking change shipped without a version bump: still 1.0.0 ▼ security
- Tool “ai_crawler_policy_check” was removed ▼ security
- Tool “cors_policy_check” was removed ▼ security
- Tool “favicon_manifest_check” was removed ▼ security
- Tool “ip_geolocation_asn_lookup” was removed ▼ security
- Tool “json_ld_schema_validator” was removed ▼ security
- Tool “sitemap_url_validator” was removed ▼ security
- Tool “broken_link_check” rewrote its description, which is the text the model reads security
- Tool “check_open_ports” rewrote its description, which is the text the model reads security
- Tool “check_robots_sitemap” rewrote its description, which is the text the model reads security
- Tool “domain_health_check” rewrote its description, which is the text the model reads security
- Tool “page_performance_check” rewrote its description, which is the text the model reads security
- Tool “pagespeed_insights” rewrote its description, which is the text the model reads security
- Tool “security_headers_audit” rewrote its description, which is the text the model reads security
- Tool “seo_audit” rewrote its description, which is the text the model reads security
- Tool “ssl_cert_check” rewrote its description, which is the text the model reads security
- Tool “ssl_labs_grade” rewrote its description, which is the text the model reads security
- Tool “structured_data_extract” rewrote its description, which is the text the model reads security
- Tool “tech_stack_fingerprint” rewrote its description, which is the text the model reads security
- Schema quality: pass → fail ▼ functional
- Destructive annotations: 0 → pass functional
- New tool “ai_readiness_audit” functional
- New tool “exposed_files_check” functional
- New tool “mcp_server_probe” functional
- New tool “smtp_server_check” functional
- New tool “subdomain_discovery” functional
- New tool “whois_lookup” functional
- “broken_link_check” added an optional parameter “viaSitemap” cosmetic
- “broken_link_check” reworded the description of “checkExternal” cosmetic
- “broken_link_check” reworded the description of “maxPages” cosmetic
- “broken_link_check” reworded the description of “url” cosmetic
- 30 Sept 26 0
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://papacasper.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=papacasper.com | CN=WE1,O=Google Trust Services,C=US | 15 Oct 2026 | 13 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | 6017f7a70e4c35b30eed5bef57d78a05 |
| SANs: papacasper.com, *.papacasper.com | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of papacasper.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| papacasper.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=31536000; includeSubDomains |
| x-content-type-options | nosniff |
| x-frame-options | SAMEORIGIN |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://papacasper.com/mcp | Verified | 200 | |
| http (plaintext) | http://papacasper.com/mcp | HTTPS enforced | 301 | https://papacasper.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
address_normalize Address Normalize ~163
Normalize 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), state names to 2-letter codes, ZIP/ZIP+4 cleanup, and a parsed breakdown (house number, street, unit, city, state, ZIP). Formatting only — it does not verify the address is deliverable. Non-US addresses get whitespace cleanup only.
| Name | Type | Req | Description |
|---|---|---|---|
| address | string | yes | Full address on one line or several, e.g. '1600 Pennsylvania Avenue Northwest, Washington, District of Columbia 20500' |
| country | string | – | ISO country code (default US; only US gets full normalization) |
No output schema declared.
No examples provided.
ai_crawler_policy_check AI Crawler Policy Check ~247
Report, 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, ChatGPT-User, OAI-SearchBot, ClaudeBot, Claude-Web, anthropic-ai, Google-Extended, PerplexityBot, CCBot, Bytespider, Applebot-Extended, Meta-ExternalAgent, Amazonbot and cohere-ai. Also reads the page's meta robots / X-Robots-Tag noai and noimageai hints and checks /llms.txt (and /llms-full.txt). Optional extra paths to test. Deterministic parsing, no AI. For a scored AI-readiness report use ai_readiness_audit; for raw robots/sitemap contents use check_robots_sitemap.
| Name | Type | Req | Description |
|---|---|---|---|
| paths | array | – | Optional extra paths to test per bot, e.g. ['/blog/', '/api/'] (max 10) |
| url | string | yes | Any URL on the site (origin is derived from it); its path is also tested |
No output schema declared.
No examples provided.
ai_readiness_audit AI Readiness Audit ~167
Score 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 and structure, structured data (JSON-LD) and Open Graph basics, agent/payment discovery files (/.well-known/x402, /openapi.json), sitemap presence, and title/meta basics. The bundle to run before/after making a site agent-friendly — for raw robots/sitemap contents only, use check_robots_sitemap; for classic search SEO only, use seo_audit.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Any URL on the site to audit (origin is derived from it) |
No output schema declared.
No examples provided.
archived_page_lookup Archived Page Lookup ~229
Find 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), HTTP status, MIME type and content digest, plus a few next-closest captures. Defaults to successful (HTTP 200) captures only. Uses the public CDX index with an availability-API fallback. Good for seeing what a page said on a past date or proving when content changed.
| Name | Type | Req | Description |
|---|---|---|---|
| alternatives | number | – | How many next-closest captures to include, 0-10 (default 4) |
| date | string | – | Target date: ISO (2015-01-01 or 2015-01-01T12:00:00Z) or Wayback timestamp (20150101). Default now |
| onlySuccessful | boolean | – | Only consider HTTP 200 captures (default true) |
| url | string | yes | Page or domain to look up, e.g. example.com or https://example.com/pricing |
No output schema declared.
No examples provided.
broken_link_check Broken Link Check ~231
Find 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 page(s) it was found on. Sitemap mode (viaSitemap: true): parse the site's sitemap.xml (following one level of sitemap-index nesting) and check the status of every URL listed in it instead. Note: some external sites (e.g. social platforms) block automated HEAD/GET requests and may show up as false positives.
| Name | Type | Req | Description |
|---|---|---|---|
| checkExternal | boolean | – | Crawl mode only: also check links pointing off-site (default true; crawling never follows off-site links) |
| maxPages | number | – | Max same-origin pages to crawl in crawl mode (default 20, capped at 50) |
| url | string | yes | Starting URL to crawl — or, in sitemap mode, the sitemap.xml URL or any page URL on the site |
| viaSitemap | boolean | – | Check the URLs listed in the site's sitemap.xml instead of crawling pages (default false) |
No output schema declared.
No examples provided.
check_open_ports Check Open Ports ~130
TCP-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, etc.) if none are given. For checking your own infrastructure's exposure — capped at 100 ports per call.
| Name | Type | Req | Description |
|---|---|---|---|
| host | string | yes | Hostname or IP to scan (no scheme) |
| ports | array | – | Specific ports to check. Defaults to a common-ports list. Max 100 ports per call. |
No output schema declared.
No examples provided.
check_robots_sitemap Robots and Sitemap Check ~121
Check 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, Amazonbot and other AI crawlers, vs wildcard/default), and llms.txt presence. For a scored, whole-site AI-readiness report use ai_readiness_audit instead.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Any URL on the site to check (origin is derived from it) |
No output schema declared.
No examples provided.
csv_to_json CSV to JSON ~266
Convert 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 default (or returns arrays), and optionally infers numbers, booleans and empty-as-null. Pass CSV text or a URL to fetch (max 2 MB, 10,000 rows returned; truncation is flagged). Deterministic, no AI.
| Name | Type | Req | Description |
|---|---|---|---|
| csv | string | – | CSV text (provide csv OR url) |
| delimiter | string | – | Field delimiter: ',', ';', '|', or 'tab' (default auto-detect) |
| header | boolean | – | Treat the first row as column names and return objects (default true); false returns arrays |
| inferTypes | boolean | – | Convert numbers, true/false, and empty cells to null (default true); false keeps every value a string |
| maxRows | number | – | Maximum data rows to return, up to 10,000 (default 10,000) |
| skipEmptyLines | boolean | – | Drop blank lines (default true) |
| url | string | – | Public URL of a CSV file to fetch instead |
No output schema declared.
No examples provided.
dns_propagation_check DNS Propagation Check ~105
Query 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 after a DNS change.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | Bare domain to query, e.g. example.com |
| recordType | string | – | Record type: A, AAAA, MX, TXT, NS, or CNAME (default A) |
No output schema declared.
No examples provided.
domain_availability_check Domain Availability Check ~128
Check 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-protection or domain-flipping research. WHOIS-based; capped at 40 variants checked per call for latency.
| Name | Type | Req | Description |
|---|---|---|---|
| checkSquats | boolean | – | Also scan typo-squat variants (default true) |
| domain | string | yes | Bare domain to check, e.g. example.com |
No output schema declared.
No examples provided.
domain_health_check Domain Health Check ~117
Check 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 deliverability detail (DKIM, DNSBL, PTR) use email_deliverability_check; for all of it plus SEO in one report use domain_report.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | Bare domain to check, e.g. example.com (no scheme/path) |
No output schema declared.
No examples provided.
domain_report Domain Report ~116
Bundle: 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. Cheaper than calling the three tools separately. Each sub-check reports independently, so a failure in one doesn't void the others.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | Bare domain to report on, e.g. example.com (no scheme/path) |
No output schema declared.
No examples provided.
email_address_validate Email Address Validate ~92
Validate 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 email_deliverability_check, which audits a whole domain's sending reputation (SPF/DKIM/DMARC/PTR/DNSBL).
| Name | Type | Req | Description |
|---|---|---|---|
| string | yes | Email address to validate |
No output schema declared.
No examples provided.
email_deliverability_check Email Deliverability Check ~151
Deep-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 lookups (Spamhaus Zen, SpamCop, Barracuda) on MX IPs. Note: public-resolver DNSBL queries are frequently rate-limited or blocked by Spamhaus, so a `listed: null` result means "unknown", not "clean" — treat null results as inconclusive, not as a clean bill of health.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | Bare domain to check, e.g. example.com |
No output schema declared.
No examples provided.
exposed_files_check Exposed Files Check ~150
Probe 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.sql, dump.sql), backup archives, phpinfo pages, .DS_Store, and similar. Reports ONLY reachability metadata (path, status, content type, size) — file contents are never returned or stored. A random-nonexistent-path baseline filters out SPA/catch-all false positives. For auditing your own sites' exposure.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Any URL on the site to probe (origin is derived from it) |
No output schema declared.
No examples provided.
favicon_manifest_check Favicon and Manifest Check ~151
Check 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, background_color, icons with sizes/purpose), each with its HTTP status, plus the theme-color meta tag. Flags broken icon links and missing 192/512 manifest icons. Deterministic HTML/JSON parsing, no AI. For a whole-page SEO audit (which includes a lighter version of this) use seo_audit.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | Page to check, usually the homepage, e.g. https://example.com |
No output schema declared.
No examples provided.
github_repo_health_check GitHub Repo Health Check ~77
Check 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.
| Name | Type | Req | Description |
|---|---|---|---|
| owner | string | yes | Repository owner (user or org) |
| repo | string | yes | Repository name |
No output schema declared.
No examples provided.
html_to_pdf HTML to PDF ~305
Render 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 short-lived download URL (valid 1 hour) with byte size, page count and SHA-256; set includeBase64 for the PDF inline (up to 3 MB). Raw HTML up to 2 MB; any external resources it loads go through the same private-address block. Pure rendering, no AI.
| Name | Type | Req | Description |
|---|---|---|---|
| format | string | – | Paper size (default A4) |
| html | string | – | Raw HTML document to render instead of a URL (max 2 MB) |
| includeBase64 | boolean | – | Also return the PDF as base64 in the response (default false; omitted if over 3 MB) |
| landscape | boolean | – | Landscape orientation (default false) |
| margin | string | – | CSS margin applied to all sides, e.g. '1cm', '0.5in', '10mm' (default '1cm') |
| printBackground | boolean | – | Include CSS backgrounds and colors (default true) |
| scale | number | – | Render scale, 0.1-2 (default 1) |
| url | string | – | Page to render (provide url OR html) |
| waitUntil | string | – | When loading counts as finished (default load) |
No output schema declared.
No examples provided.
image_resize Image Resize ~344
Download 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, JPEG, WebP, AVIF) and quality. Honors EXIF rotation. Input up to 15 MB / 50 megapixels, output up to 4096px per side. Returns a short-lived download URL (valid 1 hour) with final dimensions and byte size; set includeBase64 for the bytes inline (up to 3 MB). Deterministic, no AI.
| Name | Type | Req | Description |
|---|---|---|---|
| background | string | – | Hex color for contain padding / JPEG flattening, e.g. #ffffff (default white) |
| fit | string | – | How to fit both dimensions (default inside = keep aspect ratio, no crop) |
| format | string | – | Output format (default: same family as the source, PNG otherwise) |
| height | number | – | Target height in pixels, 1-4096 |
| includeBase64 | boolean | – | Also return the image as base64 in the response (default false; omitted if over 3 MB) |
| quality | number | – | JPEG/WebP/AVIF quality 1-100 (default 82) |
| url | string | yes | Public URL of the source image (PNG, JPEG, WebP, AVIF, GIF, TIFF, SVG) |
| width | number | – | Target width in pixels, 1-4096 (give width, height, or both) |
| withoutEnlargement | boolean | – | Never upscale a smaller source (default false) |
No output schema declared.
No examples provided.
mcp_server_probe MCP Server Probe ~118
Probe 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 depth, input-schema completeness, and naming consistency — with a 0-100 score, letter grade, and per-tool detail. Use it to vet an MCP server before connecting an agent (or paying per call) to it.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The MCP server endpoint URL, e.g. https://example.com/mcp |
No output schema declared.
No examples provided.
package_vulnerability_check Package Vulnerability Check ~125
Look 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, RubyGems, Go, Maven, NuGet, and Packagist ecosystems. Useful before adding a dependency.
| Name | Type | Req | Description |
|---|---|---|---|
| ecosystem | string | yes | Package ecosystem |
| name | string | yes | Package name |
| version | string | – | Optional exact version to check; omit to check the package generally |
No output schema declared.
No examples provided.
page_performance_check Page Performance Check ~88
Fetch 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 Google Lighthouse scores, Core Web Vitals, and real-user field data use pagespeed_insights instead.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The URL to measure |
No output schema declared.
No examples provided.
pagespeed_insights PageSpeed Insights ~128
Run 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 score — for a quick raw TTFB/size timing check from this server use page_performance_check instead. Works without an API key at low volume; set GOOGLE_PAGESPEED_API_KEY server-side for higher throughput.
| Name | Type | Req | Description |
|---|---|---|---|
| strategy | string | – | Device strategy (default mobile) |
| url | string | yes | The URL to test |
No output schema declared.
No examples provided.
phone_validate Phone Validate ~168
Validate 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, …). Pass defaultCountry for numbers written without a +country code. Offline metadata check — it does not dial or confirm the line is in service. Companion to email_address_validate.
| Name | Type | Req | Description |
|---|---|---|---|
| defaultCountry | string | – | ISO 3166-1 alpha-2 country to assume when the number has no + prefix, e.g. US, GB, DE |
| phone | string | yes | Phone number in any common format, e.g. +1 650-253-0000 or (650) 253-0000 |
No output schema declared.
No examples provided.
redirect_chain_check Redirect Chain Check ~57
Follow 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.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The starting URL to trace |
No output schema declared.
No examples provided.
safe_browsing_check Safe Browsing Check ~64
Check 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).
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The URL to check |
No output schema declared.
No examples provided.
security_headers_audit Security Headers Audit ~117
Fetch 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 foreign Origin header and flags wildcard-origin + credentials combinations and arbitrary-origin reflection). Header-level checks on a single response — for server/TLS-level checks use ssl_cert_check or ssl_labs_grade instead.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The URL to audit |
No output schema declared.
No examples provided.
seo_audit SEO Audit ~139
Fetch 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/external link counts and generic-anchor-text detection, robots meta (noindex/nofollow), structured data (JSON-LD) presence, robots.txt/sitemap.xml presence, and site chrome (favicon, apple-touch-icon, web app manifest, theme-color). Whole-page audit — for raw extracted data only use structured_data_extract, for the platform/framework use tech_stack_fingerprint.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The URL to audit |
No output schema declared.
No examples provided.
smtp_server_check SMTP Server Check ~158
Live-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 STARTTLS when offered and reports the TLS protocol and certificate (issuer, expiry). The server-side complement to email_deliverability_check (which reads DNS records only and never connects). No mail is sent and no relay attempt is made.
| Name | Type | Req | Description |
|---|---|---|---|
| host | string | yes | Mail server hostname, e.g. mail.example.com — or a bare domain, in which case its lowest-priority-number MX host is probed |
| port | number | – | SMTP port (default 25) |
No output schema declared.
No examples provided.
ssl_cert_check SSL Certificate Check ~96
Connect 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 instead.
| Name | Type | Req | Description |
|---|---|---|---|
| hostname | string | yes | Hostname to check, e.g. papacasper.com (no scheme/path) |
| port | number | – | TLS port to connect to (default 443) |
No output schema declared.
No examples provided.
ssl_labs_grade SSL Labs Grade ~126
Full 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 a deep grade; use ssl_cert_check instead for a fast expiry/issuer check. Slower (can take up to ~90s on a cold cache; SSL Labs caches results for 24h server-side).
| Name | Type | Req | Description |
|---|---|---|---|
| hostname | string | yes | Hostname to assess, e.g. example.com (no scheme/path) |
No output schema declared.
No examples provided.
structured_data_extract Structured Data Extract ~230
Fetch 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), OpenGraph/meta tags, and optional caller-supplied CSS-selector fields (e.g. { price: '.product-price', title: 'h1' }). No LLM involved — pure HTML parsing via CSS selectors, so results are exact matches only, not summarized or inferred. For a whole-page SEO audit (headings, links, images, meta lengths) use seo_audit instead.
| Name | Type | Req | Description |
|---|---|---|---|
| attr | string | – | Optional HTML attribute to extract instead of text content (e.g. 'href', 'src', 'content'). Applies to all selector fields in this call. |
| selectors | object | – | Optional map of field name -> CSS selector (e.g. { price: '.product-price', headline: 'h1' }). Each field returns an array of matched, whitespace-normalized text values in document order. |
| url | string | yes | The URL to extract from |
No output schema declared.
No examples provided.
subdomain_discovery Subdomain Discovery ~96
Enumerate 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 packets are sent to the target. Useful for attack-surface reviews, migration inventories, and finding forgotten test/staging hosts.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | Bare domain to enumerate, e.g. example.com (no scheme/path) |
No output schema declared.
No examples provided.
tech_stack_fingerprint Tech Stack Fingerprint ~104
Fetch 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 site built with?' — for on-page SEO/content signals use seo_audit, for raw structured data use structured_data_extract. Best-effort — not exhaustive, no additional paths are probed.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The URL to fingerprint |
No output schema declared.
No examples provided.
url_to_markdown URL to Markdown ~51
Fetch a URL and return its main text content as clean, readable plain text/markdown-ish output. Strips scripts, styles, and HTML tags.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | The URL to fetch |
No output schema declared.
No examples provided.
vat_validate VAT Validate ~156
Validate 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 business name and address when the member state shares them. Covers all EU states plus XI (Northern Ireland); Greece accepts GR or EL. If VIES or the member state's service is down, the call errors (API-key credits are refunded) instead of guessing.
| Name | Type | Req | Description |
|---|---|---|---|
| countryCode | string | – | 2-letter EU country code if vatNumber has no prefix, e.g. DE |
| vatNumber | string | yes | VAT number, ideally with its country prefix, e.g. IE6388047V or DE 123456789 |
No output schema declared.
No examples provided.
website_screenshot Website Screenshot ~334
Render 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), wait condition, and extra delay for late-loading content. Returns a short-lived download URL (valid 1 hour) plus pixel dimensions, byte size and SHA-256; set includeBase64 for the PNG inline (up to 3 MB). Private/internal addresses are blocked. Pure rendering, no AI. For load-time numbers use page_performance_check or pagespeed_insights instead.
| Name | Type | Req | Description |
|---|---|---|---|
| delayMs | number | – | Extra wait after load before capturing, 0-5000 ms (default 0) |
| deviceScaleFactor | number | – | Device pixel ratio, 1-2 (default 1; 2 = retina) |
| fullPage | boolean | – | Capture the full scrolling page instead of just the viewport (default false; capped at 10,000px tall) |
| height | number | – | Viewport height in CSS pixels, 240-2160 (default 800) |
| includeBase64 | boolean | – | Also return the PNG as base64 in the response (default false; omitted if over 3 MB) |
| url | string | yes | Page to capture, e.g. https://example.com (https:// is assumed if no scheme) |
| waitUntil | string | – | When navigation counts as finished (default load) |
| width | number | – | Viewport width in CSS pixels, 320-1920 (default 1280) |
No output schema declared.
No examples provided.
websocket_endpoint_check WebSocket Endpoint Check ~87
Test 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 handshake before you wire real traffic to it.
| Name | Type | Req | Description |
|---|---|---|---|
| url | string | yes | WebSocket URL to test, e.g. wss://example.com/socket |
No output schema declared.
No examples provided.
whois_lookup WHOIS Lookup ~90
Look 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, use domain_health_check; for a combined report, use domain_report.
| Name | Type | Req | Description |
|---|---|---|---|
| domain | string | yes | Bare domain to look up, e.g. example.com (no scheme/path) |
No output schema declared.
No examples provided.
How do I install the mcp-toolbelt server?
mcp-toolbelt is a hosted endpoint at https://papacasper.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · papacasper.com
claude mcp add --transport http com-papacasper-mcp-toolbelt 'https://papacasper.com/mcp'
What is the mcp-toolbelt server?
mcp-toolbelt is listed in the public MCP registry as com.papacasper/mcp-toolbelt. 29 DNS, SEO, SSL, security, WHOIS & mail tools for AI agents. Pay per call (x402) or card API key. This page covers its hosted endpoint (https://papacasper.com/mcp).
Is the mcp-toolbelt server safe to use?
mcp-toolbelt scores 84 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the mcp-toolbelt server expose?
mcp-toolbelt exposes 39 tools: url_to_markdown, security_headers_audit, redirect_chain_check, page_performance_check, structured_data_extract, and 34 more. Their descriptions and schemas cost roughly 5,822 tokens of context every time the server is loaded.
Does the mcp-toolbelt server require authentication?
No. We connected to mcp-toolbelt without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the mcp-toolbelt server still maintained?
mcp-toolbelt is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the mcp-toolbelt server?
VerifyMCP ran 13 checks on mcp-toolbelt, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.