HTML entities MCP.
MCP servers
Compare source listings, connection options and authentication requirements.
Showing 27,769–27,792 of 165,917 resultsPage 1158 of 6,914
Candidate groups, not verified unique MCPs. How grouping works
Htmlpdf Transform Mcp connects AI agents to real public APIs via MCP. Tools include
HTMLRadar turns a web page into a link you control: only the people you choose can open it, you see who read it and which sections they stayed on, and you can update it without sending a new link. Your agent publishes the page, checks who read it and updates it, while you decide who gets in. The page goes out from the conversation it was made in. Claude publishes it as a link for each person, with the gate you ask for: company only, an e-mail code, a password or an expiry. Nothing to download and upload again. You ask who read it, in plain words. Claude finds what you sent last week and tells you who opened it, for how long, and which parts they read. A fix reaches everyone on the link they already have. Claude changes only what you asked, puts every image back exactly, and keeps the old version in the history. Nobody gets a second e-mail. Readers need no account and nothing to install. We record who opened it, when, for how long and which sections. Never keystrokes or mouse movements, no third-party trackers, and readers' network addresses are not stored. Signing in also creates your HTMLRadar account. Two tracked links are free, with the first five readers of each shown; Pro is $19 a month.
HTML → text MCP.
Claude and other AI tools generate HTML constantly, from reports to landing pages to prototypes, but there's no easy way to share it or know if anyone looked. HTMLvault turns any HTML into a clean, trackable link in seconds: visitors, geography, device, referrer, time on page. Through this connector, Claude can publish links one at a time or in bulk from a template, edit or delete them, and pull analytics, all without leaving the conversation. Draft something, say "vault this," and get back a link ready to send. Every link is also scanned for PII and secrets before it publishes (Enterprise: your own AI scanning on top), with password protection and configurable retention available. Free: 50 links/month, 30-day expiry. Pro/Enterprise: unlimited links and white-label with your own domain. Full reference: htmlvault.com/docs/mcp.
RU INN/OGRN, banks, geo, WHOIS. Agent self-registers via register_agent. 20 free/day.
Answer questions from PDFs converted to.htpd: exact text with pages, or 'Not found in this file.'
HTS MCP — US import tariff rates via the USITC Harmonized Tariff Schedule.
HTTP/REST client with saved collections, env secrets, and SSRF-safe host allowlisting.
Free MCP troubleshooting-preview tools; purchases stay human-directed.
HTTP header analysis — security headers, cache, server detection. x402 micropayment.
Send one HTTP request, or one per row of a dataset, CSV or Google Sheet, and get the response back
Short catalog of common HTTP status codes.
httpbin MCP.
HTTP Cat MCP — wraps http.cat (free, no auth)
PageHub is a website builder, and this server lets your AI agent do the building. Ask for a site and the agent picks a template, adds pages from a library of ready sections, sets colors and fonts, and fills in your copy and photos. It can screenshot the draft in a real browser and run SEO and accessibility checks before you look. Every change lands in a draft. Nothing goes live until you or the agent publishes, so it's safe to point at a site that's already up. When you're ready, publish to a free pagehub.dev address or attach your own domain; the agent gives you the DNS records to add. Beyond pages, it can manage collections for blogs and listings, sell through Stripe, edit site emails, set redirects and analytics tags, and invite collaborators. It's a hosted server: add https://pagehub.dev/api/mcp to your client and sign in with your PageHub account in the browser. Nothing to install. The free plan works: 1 published site, 20 pages, 1 custom domain.
HTTP status code reference MCP.
HttpStatus MCP gives Claude nine tools for debugging and inspecting HTTP endpoints, built by HttpStatus.com. Tools: - check_url_status: fetch a URL and report its status code, headers and timing - trace_redirects: follow a redirect chain hop by hop - check_ssl: inspect a site's TLS certificate, issuer and expiry - dns_lookup: resolve A, AAAA, CNAME, MX, TXT and other records - check_cors: test how an endpoint responds to cross-origin requests - scan_security_headers: audit headers such as CSP, HSTS and X-Frame-Options - decode_jwt: decode a JWT's header and payload - generate_status_url: build a URL that returns any HTTP status code - generate_dummy_response: produce free public test endpoints for API development Typical uses: figuring out why a page returns a 404 or 502, finding redirect loops after a migration, checking a certificate before it expires, debugging CORS errors, and reviewing a site's security headers. The tools are stateless and only make requests to public hosts. Nothing is stored. Sign-in uses standard OAuth with no account needed beyond approving access.
AI-agent website mirroring and offline archive browsing over MCP, powered by HTTrack.
Reduces AI Agent token usage by 40% via three-stage SOP workflow.
Community preview of HuaweiCloud DevKit MCP server (official: io.github.huaweicloud)
Multiple Google accounts (Gmail, Calendar, Drive, Contacts, Tasks) in one Claude connector.
Standardized, restatement-aware SEC + European (ESEF) XBRL fundamentals, served to your agent.
Hubbl scans your Salesforce orgs and turns the results into context Claude can use. Get read-only access across configuration and code (objects, fields, flows, triggers, workflows, Apex, and code-quality findings), access and licensing (profiles, permission sets, license usage, connected apps, installed packages), and adoption (login activity, object usage, cloud usage, package usage, org limits, field utilization), alongside Hubbl's prioritized issues and recommendations for keeping orgs secure, well-architected, and clean. Ask what to fix first, compare one org or many, and pull step-by-step remediation guidance for any finding. The server performs no writes, so nothing in Salesforce or Hubbl changes.
What this catalog covers
- Source listings
- 167,897
- Candidate groups
- 168,273
- Setup-eligible endpoints
- 30,743
Sources observed 2026-10-24–2026-11-12. Listings can overlap across sources. Groups are identity candidates; setup eligibility is not a successful connection test.
SourcesMCP data from Glama connectorsMCP data from Glama source codeOfficial MCP RegistryClaude connector directoryAPI Tracker · publisher documentationSlack MCP directory
Default browsing excludes 2,356 specialized utility groups across the catalog. They remain available through keyword search and direct links. This editorial filter does not change the indexed totals or establish publisher quality.
Categories currently cover records matched to our reviewed catalog; other listings remain Uncategorized. Source-only projects have no generated connection option. Browse reviewed official MCPs →
- Glama connectors
API result set; pagination may cap at approximately 1,000 connectors. Not exhaustive.
- Glama source code
Complete chronological source-code catalog response; includes source-reported author classifications, not publisher attestations or ready-to-use endpoints.
- Official MCP Registry
Complete paginated registry response; registry membership is not publisher verification.
- Claude connector directory
Complete public Claude directory MCP components. Source tiers, tools, icons and sign-in hints are declarations, not publisher or runtime verification.
- API Tracker · publisher documentation
Reviewed publisher and third-party remote, local and setup-only MCP listings. Publisher status is retained per exact connection. Discoverability does not establish connection readiness.
- Slack MCP directory
Reviewed additions discovered through the public Slack Marketplace MCP category. Complete discovery inventory is retained separately; membership does not prove external-client compatibility.
Listings are grouped by exact public endpoints, exact package sets, or explicit reviewed identity bindings. Shared names or repositories alone do not merge implementations. Official includes publisher evidence and accepted source author classifications. It does not mean independently verified, runtime-tested or security-certified.