Fetcher is a remote MCP server that gives an AI agent 19 tools, among them check_domain, check_robots, diff_pages. It answers at https://api.fetcher.cloud/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
The web capability layer for AI agents: render, extract, DNS, SSL, WHOIS & more via x402.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
check_domain | Check domain availability across TLDs via RDAP. Set enriched=true for DNS, age, and Wayback history. (domain-dns; $0.004/call in USDC via x402, 50 free/day). Inputs: name, tlds, enriched |
check_robots | Parse robots.txt; answer whether a user-agent may crawl a path; list sitemaps. (web-intel; $0.002/call in USDC via x402, 50 free/day). Inputs: host, path, user_agent |
diff_pages | Compare two pages (or one page vs its latest Wayback snapshot); return what changed. (content; $0.008/call in USDC via x402, 25 free/day). Inputs: url_a, url_b |
dns_lookup | Full DNS record dump (A/AAAA/MX/NS/TXT/SOA/CAA/CNAME) for a host. (domain-dns; $0.003/call in USDC via x402, 50 free/day). Inputs: host |
extract_content | Extract a page's main content as clean Markdown + text with metadata. (content; $0.005/call in USDC via x402, 30 free/day). Inputs: url, mode |
extract_pdf | Extract text + metadata from a PDF URL (text-based PDFs). (content; $0.01/call in USDC via x402, 20 free/day). Inputs: url, max_pages |
find_favicon | Find a site's best icon/logo. (web-intel; $0.002/call in USDC via x402, 50 free/day). Inputs: host |
generate_qr | Generate a QR code (SVG) for text or a URL. (utility; $0.002/call in USDC via x402, 50 free/day). Inputs: data, ecc |
get_feed | Discover and parse a site's RSS/Atom feed into JSON items. (content; $0.003/call in USDC via x402, 40 free/day). Inputs: url, limit |
get_oembed | Rich embed (oEmbed) data for a media URL (YouTube, Vimeo, X, Spotify...). (content; $0.002/call in USDC via x402, 50 free/day). Inputs: url |
guard_inspect | Screen untrusted content (web pages, emails, tool output) for prompt-injection/manipulation before your agent trusts it. Returns a risk score + reasons; a screening signal, not a guarantee. (security; $0.005/call in USDC via x402, 30 free/d Inputs: text, deep |
guard_tx | Pre-sign wallet firewall: decode a transaction and flag unlimited approvals, setApprovalForAll, scam addresses, and spend-cap breaches before signing. Returns a risk verdict + reasons. (security; $0.008/call in USDC via x402, 25 free/day). Inputs: to, data, value, chain, from |
inspect_headers | HTTP response headers + security-header analysis for a URL. (web-intel; $0.002/call in USDC via x402, 50 free/day). Inputs: url |
render_page | Render a JavaScript page in a real browser; returns rendered HTML, text, optional screenshot. (browser; $0.02/call in USDC via x402, 10 free/day). Inputs: url, screenshot, full_page |
resolve_url | Follow a URL's full redirect chain; return final URL, hops, and metadata. (web-intel; $0.003/call in USDC via x402, 50 free/day). Inputs: url |
screenshot_page | Screenshot a page (real browser) as a base64 PNG/JPEG. (browser; $0.02/call in USDC via x402, 10 free/day). Inputs: url, full_page |
ssl_lookup | TLS certificate details (issuer, expiry, SANs) via Certificate Transparency logs. (domain-dns; $0.004/call in USDC via x402, 40 free/day). Inputs: host |
unfurl_url | Link preview card (title, description, image, favicon) for any URL. (content; $0.003/call in USDC via x402, 50 free/day). Inputs: url |
whois_lookup | Deep domain registration record via RDAP (registrar, dates, nameservers, DNSSEC). (domain-dns; $0.005/call in USDC via x402, 40 free/day). Inputs: domain |
Every block below points at https://api.fetcher.cloud/mcp. Pick your client and copy.
claude mcp add --transport http fetcher https://api.fetcher.cloud/mcp
{
"mcpServers": {
"fetcher": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://api.fetcher.cloud/mcp"]
}
}
}{
"mcpServers": {
"fetcher": {
"url": "https://api.fetcher.cloud/mcp"
}
}
}{
"servers": {
"fetcher": {
"type": "http",
"url": "https://api.fetcher.cloud/mcp"
}
}
}{
"context_servers": {
"fetcher": {
"url": "https://api.fetcher.cloud/mcp"
}
}
}{
"mcpServers": {
"fetcher": {
"serverUrl": "https://api.fetcher.cloud/mcp"
}
}
}{
"mcpServers": {
"fetcher": {
"url": "https://api.fetcher.cloud/mcp"
}
}
}name: Fetcher
version: 0.0.1
schema: v1
mcpServers:
- name: Fetcher
type: streamable-http
url: https://api.fetcher.cloud/mcp{
"mcpServers": {
"fetcher": {
"httpUrl": "https://api.fetcher.cloud/mcp"
}
}
}{
"mcpServers": {
"fetcher": {
"type": "http",
"url": "https://api.fetcher.cloud/mcp"
}
}
}{
"mcpServers": {
"fetcher": {
"url": "https://api.fetcher.cloud/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fapi.fetcher.cloud%2Fmcp&type=streamable_http&id=fetcher&name=Fetcher
It answered our last check on 17 October 2026 in 94 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by fetcher.cloud and served from api.fetcher.cloud, the vendor's own domain: https://api.fetcher.cloud/mcp.
19, as returned by the server's own tools/list on 9 September 2026: check_domain, check_robots, diff_pages, dns_lookup, extract_content, extract_pdf, find_favicon, generate_qr, and 11 more.
It answered our last check on 17 October 2026 in 94 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://api.fetcher.cloud/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: cloud.fetcher. Endpoint host: api.fetcher.cloud. ARD identifier: urn:air:cloud.fetcher:mcp:fetcher.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.