fetcher MCP server
cloud.fetcher/fetcherfetcher.cloudstreamable-httpv1.1.3Scanned
The web capability layer for AI agents: render, extract, DNS, SSL, WHOIS & more via x402.
19 tools: 1 do something that can't be undone, 7 change things and 11 only read.
- Reads private data · 1
- Reads text others write · 7
- Can send data out · 10
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here does something that can't be undone. Govern it.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the fetcher MCP server can do
The fetcher MCP server is published by fetcher.cloud, a domain the MCP Registry verified. It has 19 tools. It can do things that cannot be undone, such as sending, paying or publishing (guard_tx) and create or change data (7 tools: render_page, extract_content, unfurl_url, check_robots and 3 more), but cannot delete data. 11 tools only read.
1 tool reads private data (guard_inspect); 7 tools bring in text other people can write (screenshot_page, resolve_url, get_feed and 4 more); 10 tools can send data out of your system (render_page, screenshot_page, extract_content and 7 more). On its own it has all three parts of a prompt-injection exfiltration path: private data, text others write, and a way out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 10, 2026, version 1.1.3.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
19 tools
Can't be undone 1Claude Code: ask
guard_txPre-sign wallet firewall: decode a transaction and flag unlimited approvals, setApprovalForAll, scam addresses, and spend-cap breaches before signing.Can send data outNo findings
Why it is in this group
- The input addresses people (input.to): what it sends cannot be taken back.
What it can reach
- outboundThe input takes a destination (input.to): what the tool writes goes there.
Description, as the server wrote it 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).
Changes things 7Claude Code: ask
check_domainCheck domain availability across TLDs via RDAP.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it 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).
check_robotsParse robots.txt; answer whether a user-agent may crawl a path; list sitemaps.Reads text others writeNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- untrusted-inputThe description's first sentence says "crawl": it reads web pages, which anyone can write.
Description, as the server wrote it 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).
extract_contentExtract a page's main content as clean Markdown + text with metadata.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Extract a page's main content as clean Markdown + text with metadata. (content; $0.005/call in USDC via x402, 30 free/day).
extract_pdfExtract text + metadata from a PDF URL (text-based PDFs).Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Extract text + metadata from a PDF URL (text-based PDFs). (content; $0.01/call in USDC via x402, 20 free/day).
generate_qrGenerate a QR code (SVG) for text or a URL.No findings
Why it is in this group
- The name "generate_qr" says "generate": a word for a change.
Description, as the server wrote it Generate a QR code (SVG) for text or a URL. (utility; $0.002/call in USDC via x402, 50 free/day).
render_pageRender a JavaScript page in a real browser; returns rendered HTML, text, optional screenshot.Can send data outNo findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it 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).
unfurl_urlLink preview card (title, description, image, favicon) for any URL.Can send data outNo findings
Why it is in this group
- The description's first verb is "link": a word for a change.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Description, as the server wrote it Link preview card (title, description, image, favicon) for any URL. (content; $0.003/call in USDC via x402, 50 free/day).
Only reads 11Show 11 read-only tools
diff_pagesCompare two pages (or one page vs its latest Wayback snapshot); return what changed.No findings
Why it is in this group
- The name "diff_pages" says "diff": a word for reading.
Description, as the server wrote it 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).
dns_lookupFull DNS record dump (A/AAAA/MX/NS/TXT/SOA/CAA/CNAME) for a host.No findings
Why it is in this group
- The name "dns_lookup" says "lookup": a word for reading.
Description, as the server wrote it 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).
find_faviconFind a site's best icon/logo.No findings
Why it is in this group
- The name "find_favicon" says "find": a word for reading.
Description, as the server wrote it Find a site's best icon/logo. (web-intel; $0.002/call in USDC via x402, 50 free/day).
get_feedDiscover and parse a site's RSS/Atom feed into JSON items.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_feed" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "rss": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Discover and parse a site's RSS/Atom feed into JSON items. (content; $0.003/call in USDC via x402, 40 free/day).
get_oembedRich embed (oEmbed) data for a media URL (YouTube, Vimeo, X, Spotify...).Reads text others writeCan send data outNo findings
Why it is in this group
- The name "get_oembed" says "get": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Rich embed (oEmbed) data for a media URL (YouTube, Vimeo, X, Spotify...). (content; $0.002/call in USDC via x402, 50 free/day).
guard_inspectScreen untrusted content (web pages, emails, tool output) for prompt-injection/manipulation before your agent trusts it.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "guard_inspect" says "inspect": a word for reading.
What it can reach
- private-dataThe description's first sentence says "email": it reads mail.
- untrusted-inputThe description's first sentence says "web": it reads web pages, which anyone can write.
Description, as the server wrote it 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/day).
inspect_headersHTTP response headers + security-header analysis for a URL.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "inspect_headers" says "inspect": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "http": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it HTTP response headers + security-header analysis for a URL. (web-intel; $0.002/call in USDC via x402, 50 free/day).
resolve_urlFollow a URL's full redirect chain; return final URL, hops, and metadata.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "resolve_url" says "resolve": a word for reading.
What it can reach
- untrusted-inputThe name "resolve_url" says "resolve" and "url": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "url": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it 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).
screenshot_pageScreenshot a page (real browser) as a base64 PNG/JPEG.Reads text others writeCan send data outNo findings
Why it is in this group
- The name "screenshot_page" says "screenshot": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "screenshot" and "browser": it reads web pages, which anyone can write.
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Screenshot a page (real browser) as a base64 PNG/JPEG. (browser; $0.02/call in USDC via x402, 10 free/day).
ssl_lookupTLS certificate details (issuer, expiry, SANs) via Certificate Transparency logs.No findings
Why it is in this group
- The name "ssl_lookup" says "lookup": a word for reading.
Description, as the server wrote it TLS certificate details (issuer, expiry, SANs) via Certificate Transparency logs. (domain-dns; $0.004/call in USDC via x402, 40 free/day).
whois_lookupDeep domain registration record via RDAP (registrar, dates, nameservers, DNSSEC).No findings
Why it is in this group
- The name "whois_lookup" says "lookup": a word for reading.
Description, as the server wrote it Deep domain registration record via RDAP (registrar, dates, nameservers, DNSSEC). (domain-dns; $0.005/call in USDC via x402, 40 free/day).
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
70 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 1 private-data tool breaks every one.
- Reads private data1
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write7
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out10
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__fetcher__guard_inspect"
]
}
}Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 20, 2026, 18:32 UTC, unchanged since Nov 20, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 11
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 11 tools that change things (1 irreversible, 10 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://api.fetcher.cloud/mcp: tools/list returned 25 tools to an anonymous client, including guard_tx (irreversible), render_page (write), extract_content (write), unfurl_url (write), check_robots (write) and 6 more
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 8 to 11
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
PostureRemote posture changed. Tools that change things, listed without credentials: 8 -> 11.View diff
- Tools that change things, listed without credentials: 8 to 11
Install
Pinned to version 1.1.3. Values in angle brackets are yours to fill in.
claude mcp add --transport http fetcher https://api.fetcher.cloud/mcpclaude mcp add --transport http fetcher https://api.fetcher.cloud/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__fetcher__find_favicon",
"mcp__fetcher__dns_lookup",
"mcp__fetcher__ssl_lookup",
"mcp__fetcher__whois_lookup",
"mcp__fetcher__diff_pages",
"mcp__fetcher__guard_inspect"
],
"ask": [
"mcp__fetcher__render_page",
"mcp__fetcher__screenshot_page",
"mcp__fetcher__extract_content",
"mcp__fetcher__resolve_url",
"mcp__fetcher__unfurl_url",
"mcp__fetcher__get_feed",
"mcp__fetcher__get_oembed",
"mcp__fetcher__check_robots",
"mcp__fetcher__inspect_headers",
"mcp__fetcher__extract_pdf",
"mcp__fetcher__generate_qr",
"mcp__fetcher__guard_tx",
"mcp__fetcher__check_domain"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as fetcher. Review it before you use it.
Capability tags behind 12 rules
- mcp__fetcher__render_page outbound
- mcp__fetcher__screenshot_page untrusted-input, outbound
- mcp__fetcher__extract_content outbound
- mcp__fetcher__resolve_url untrusted-input, outbound
- mcp__fetcher__unfurl_url outbound
- mcp__fetcher__get_feed untrusted-input, outbound
- mcp__fetcher__get_oembed untrusted-input, outbound
- mcp__fetcher__check_robots untrusted-input
- mcp__fetcher__inspect_headers untrusted-input, outbound
- mcp__fetcher__extract_pdf outbound
- mcp__fetcher__guard_inspect private-data, untrusted-input
- mcp__fetcher__guard_tx outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/cloud.fetcher/fetcher/verify?hash=08976f2e929e1b155772baa73252cc06e2d83832151cd13d3d97f0cae53b4c3d" | jq -e '.changed == false'Pinned hash 08976f2e929e, from Nov 10, 2026, 08:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/cloud.fetcher/fetcher/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/cloud.fetcher/fetcher)Source: MCP Registry · repository. Synced Oct 21, 2026, 17:46 UTC.
fetcher MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the fetcher MCP server safe?
- No scan can promise that. What its definitions show: 19 tools, 8 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the fetcher MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the fetcher MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: guard_tx.
What tools does the fetcher MCP server have?
- 19 tools: 1 irreversible, 7 write, 11 read. guard_tx, render_page, extract_content, unfurl_url, check_robots, extract_pdf, generate_qr, check_domain and 11 more.
Does the fetcher MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the fetcher MCP server send data to outside services?
- 10 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): render_page, screenshot_page, extract_content, resolve_url, unfurl_url, get_feed and 4 more.
Has the fetcher MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 10, 2026.