FernTool Network Tools MCP server
com.ferntool/ipferntool.comstreamable-httpv1.2.0Scanned
24 free tools: IP/VPN lookup, WHOIS, DNS, SPF/DMARC, site up/down, redirects, time zones. No key.
25 tools: 1 do something that can't be undone, 13 change things and 11 only read.
- Reads private data · 4
- Reads text others write · 4
- Can send data out · 4
- 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 FernTool Network Tools MCP server can do
The FernTool Network Tools MCP server is published by ferntool.com, a domain the MCP Registry verified. It has 25 tools. It can do things that cannot be undone, such as sending, paying or publishing (convert_timezone) and create or change data (13 tools: reverse_dns, subnet_calc, estimate_ai_cost, make_qr_code and 9 more), but cannot delete data. 11 tools only read.
4 tools read private data (lookup_ip, whois_lookup, analyze_email_headers and 1 more); 4 tools bring in text other people can write (dns_lookup, check_website_status, analyze_email_headers and 1 more); 4 tools can send data out of your system (convert_timezone, check_website_status, trace_redirects and 1 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, and its tools changed 2 times since Anlyon Radar first saw them.
Last scanned Nov 9, 2026, version 1.2.0.
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.
25 tools
Can't be undone 1Claude Code: ask
convert_timezoneConvert a time between time zones with daylight saving applied (you cannot do this reliably yourself).Can send data outNo findings
Why it is in this group
- The name "convert_timezone" says "convert": a word for a change.
- 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 Convert a time between time zones with daylight saving applied (you cannot do this reliably yourself). from/to accept IANA zones (Africa/Johannesburg), common abbreviations (SAST, EST, PST, GMT, CET, IST=India, CST=US Central) or big cities. Omit time for now. Returns each local date, time, UTC offset, abbreviation, hour difference and whether it is the next/previous day.
Changes things 13Claude Code: ask
check_dns_propagationCheck whether a DNS change has spread: asks the domain's own authoritative name server (when reachable) and 8 big public resolvers (Cloudflare, Google, OpenDNS, AdGuard, NextDNS, C…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 whether a DNS change has spread: asks the domain's own authoritative name server (when reachable) and 8 big public resolvers (Cloudflare, Google, OpenDNS, AdGuard, NextDNS, Control D, CleanBrowsing, AliDNS) over DoH, marks which are up to date, and gives the remaining cache time (TTL) of stale answers.
check_email_securityCan someone fake (spoof) email from a domain?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 Can someone fake (spoof) email from a domain? Reads SPF (counts the 10 DNS-lookup limit, follows includes), DMARC (policy, pct, reports, inherited from the parent domain) and DKIM keys (common selectors, or the one given), detects the email provider from MX, and returns a plain verdict (protected / partial / unprotected) plus the exact TXT records to add.
check_website_legitIs this website legit or a scam?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 Is this website legit or a scam? Follows the URL (redirects included) and returns plain-language warning signs: domain age from RDAP (scam shops are usually days or weeks old), look-alike brand names (banks, SARS, couriers, Takealot, PayPal, Apple…), risky domain endings and scam words, look-alike letters, HTTPS, whether the domain receives email and has DMARC. verdict: no_signs, mostly_ok, caution or likely_scam. Warning signs only; not a malware scan.
convert_timestampConvert a Unix timestamp (seconds, milliseconds, microseconds or nanoseconds, auto-detected) to a readable date, or a date/time string (e.g.No findings
Why it is in this group
- The name "convert_timestamp" says "convert": a word for a change.
Description, as the server wrote it Convert a Unix timestamp (seconds, milliseconds, microseconds or nanoseconds, auto-detected) to a readable date, or a date/time string (e.g. 2026-12-25 09:00, read in the given time zone unless it has its own offset) to a Unix timestamp. Also returns weekday, ISO week and how long ago or until.
date_calcExact calendar maths.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 Exact calendar maths. With end: days between two dates (plus weeks, months+days, weekdays Mon-Fri, weekend days). With add_days/add_weeks/add_months/add_years (negative to subtract): the resulting date and weekday; business_days=true skips weekends. Use this instead of counting days yourself.
estimate_ai_costEstimate token count and USD API cost of a text across major AI models (OpenAI GPT, Anthropic Claude, Google Gemini), and whether it fits each context window.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 Estimate token count and USD API cost of a text across major AI models (OpenAI GPT, Anthropic Claude, Google Gemini), and whether it fits each context window. Token counts are approximate. Pass text, or tokens directly.
generate_spf_recordBuild one valid SPF TXT record for a domain from the services that send its email (e.g.No findings
Why it is in this group
- The name "generate_spf_record" says "generate": a word for a change.
Description, as the server wrote it Build one valid SPF TXT record for a domain from the services that send its email (e.g. microsoft365, google, mailchimp, sendgrid, website). Optionally reads the domain's current SPF record and MX first (keeps unknown entries, warns about services it would drop), adds extra IPs/includes, and counts DNS lookups live against the 10-lookup limit. Returns the record, DNS name, lookup count, notes and a starter DMARC record. Service ids: microsoft365, google, zoho, proton, fastmail, icloud, mimecast_za, mimecast, website, mx, shopify, mailchimp, mandrill, brevo, mailerlite, constantcontact, campaignmonitor, mailjet, sendpulse, sendgrid, mailgun, amazonses, postmark, zendesk, freshdesk, helpscout, salesforce.
make_qr_codeCreate a static QR code (never expires) for a URL, Wi-Fi string (WIFI:T:WPA;S:name;P:pass;;), mailto:, tel: or any text up to 2000 characters.No findings
Why it is in this group
- The description's first verb is "create": a word for a change.
Description, as the server wrote it Create a static QR code (never expires) for a URL, Wi-Fi string (WIFI:T:WPA;S:name;P:pass;;), mailto:, tel: or any text up to 2000 characters. Returns an SVG string plus a ferntool.com image URL that renders the same code.
pick_randomFairly pick random winners from a list, shuffle a list, or split people into random even teams, using a cryptographically secure generator (you cannot choose fairly at random yours…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 Fairly pick random winners from a list, shuffle a list, or split people into random even teams, using a cryptographically secure generator (you cannot choose fairly at random yourself). Use for giveaways, raffles, "who goes first", random order or team splits. An item listed twice has twice the chance unless dedupe=true.
random_numberFair, cryptographically secure random integers (you cannot produce real randomness yourself).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 Fair, cryptographically secure random integers (you cannot produce real randomness yourself). min and max are inclusive. unique=true for no repeats (raffles, lotto, picking winners). For a coin flip use min 0, max 1; for dice use min 1, max 6.
reverse_dnsReverse DNS (PTR) lookup for an IPv4/IPv6 address, with forward-confirmation check.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 Reverse DNS (PTR) lookup for an IPv4/IPv6 address, with forward-confirmation check.
subnet_calcIPv4/IPv6 CIDR subnet calculator: network, netmask, wildcard, broadcast, first/last usable host, total and usable addresses, block type.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 IPv4/IPv6 CIDR subnet calculator: network, netmask, wildcard, broadcast, first/last usable host, total and usable addresses, block type. Optional split lists the smaller subnets (e.g. the /64s in a /48).
trace_redirectsWhere does a link really go?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 Where does a link really go? Follows a URL (short links like bit.ly, tracking links, QR code links) hop by hop without a browser: every redirect with status code (301/302/307/308/meta refresh), final URL and page title, plus warning signs (ends on a different site, domain registered < 30 days ago, punycode look-alike name, bare IP, no HTTPS, loops, long chains) and a copy of the final URL with tracking parameters removed. Does not scan pages for malware. Max 10 hops; cached 60 s.
Only reads 11Show 11 read-only tools
ai_service_statusLive status of AI services (ChatGPT/OpenAI, Claude, Gemini API, GitHub Copilot, Perplexity, Cohere) read from their official status pages, cached ~60s.Reads private dataReads text others writeNo findings
Why it is in this group
- The name "ai_service_status" says "status": a word for reading.
What it can reach
- private-dataThe description's first sentence says "chat": it reads messages.
- untrusted-inputThe description's first sentence says "chat": it reads messages, which other people can write.
Description, as the server wrote it Live status of AI services (ChatGPT/OpenAI, Claude, Gemini API, GitHub Copilot, Perplexity, Cohere) read from their official status pages, cached ~60s. level is up, degraded, down or unknown.
analyze_email_headersIs this email real or fake?Reads private dataReads text others writeNo findings
Why it is in this group
- The name "analyze_email_headers" says "analyze": a word for reading.
What it can reach
- private-dataThe name "analyze_email_headers" says "analyze" and "email": it reads mail.
- private-dataThe description's first sentence says "email": it reads mail.
- untrusted-inputThe name "analyze_email_headers" says "analyze" and "email": it reads inbound email, which other people can write.
- untrusted-inputThe description's first sentence says "email": it reads inbound email, which other people can write.
Description, as the server wrote it Is this email real or fake? Paste the raw headers of an email (Gmail Show original, Outlook View message details). Returns who really sent it (From, Reply-To, Return-Path), the SPF/DKIM/DMARC results recorded by the receiving provider, look-alike or fake sender names (banks, SARS, couriers, free-mail accounts posing as companies), every Received hop with delays, the sending server IP with country/network, and a verdict: verified, unverified or suspicious. Nothing is stored.
batch_lookup_ipLook up 1-100 IPv4/IPv6 addresses at once.No findings
Why it is in this group
- The name "batch_lookup_ip" says "lookup": a word for reading.
Description, as the server wrote it Look up 1-100 IPv4/IPv6 addresses at once. Each result has version, scope, country, timezone, ASN, network owner and flags (is_tor, is_datacenter, provider).
check_website_statusIs a website down?Reads text others writeCan send data outNo findings
Why it is in this group
- The name "check_website_status" says "status": a word for reading.
What it can reach
- untrusted-inputThe name "check_website_status" says "status" and "website": it reads web pages, which anyone can write.
- untrusted-inputThe description's first sentence says "website": 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 Is a website down? Resolves its DNS and loads the URL once (10 s timeout) from FernTool's Cloudflare edge, then returns verdict (up/down), reason (ok, blocked_bot, page_not_found, server_error, timeout, tls, dns_nxdomain...), HTTP status, response time, final URL after redirects and server country/network. One vantage point only; results cached 30 s.
count_wordsExactly count words, characters (with and without spaces), sentences and paragraphs in a text, with reading/speaking time and the most repeated words.No findings
Why it is in this group
- The name "count_words" says "count": a word for reading.
Description, as the server wrote it Exactly count words, characters (with and without spaces), sentences and paragraphs in a text, with reading/speaking time and the most repeated words. Use this instead of estimating counts yourself.
dns_lookupResolve DNS records for a domain via Cloudflare 1.1.1.1 DNS-over-HTTPS.Reads text others writeNo findings
Why it is in this group
- The name "dns_lookup" says "lookup": a word for reading.
What it can reach
- untrusted-inputThe description's first sentence says "resolve" and "http": it reads web pages, which anyone can write.
Description, as the server wrote it Resolve DNS records for a domain via Cloudflare 1.1.1.1 DNS-over-HTTPS. Types: A, AAAA, MX, TXT, NS, CNAME, SOA (default: all).
get_current_timeGet the exact current date and time (you cannot know it otherwise).No findings
Why it is in this group
- The name "get_current_time" says "get": a word for reading.
Description, as the server wrote it Get the exact current date and time (you cannot know it otherwise). Returns Unix seconds and milliseconds, ISO 8601 in UTC and in the requested IANA time zone, weekday, ISO week and day of year.
get_my_ipReturn the public IP address (and ISP, ASN, location, timezone) of the caller as seen by FernTool.No findings
Why it is in this group
- The name "get_my_ip" says "get": a word for reading.
Description, as the server wrote it Return the public IP address (and ISP, ASN, location, timezone) of the caller as seen by FernTool. Note: for remote agents this is the IP of the machine calling the MCP server.
lookup_ipValidate an IPv4/IPv6 address and return its version, scope (public/private/loopback/...), country, ASN and network owner (DB-IP Lite + IPtoASN data).Reads private dataNo findings
Why it is in this group
- The name "lookup_ip" says "lookup": a word for reading.
What it can reach
- private-dataThe description's first sentence says "validate" and "db": it reads databases.
Description, as the server wrote it Validate an IPv4/IPv6 address and return its version, scope (public/private/loopback/...), country, ASN and network owner (DB-IP Lite + IPtoASN data).
validate_ipCheck whether a string is a valid IPv4 or IPv6 address and classify it.No findings
Why it is in this group
- The name "validate_ip" says "validate": a word for reading.
Description, as the server wrote it Check whether a string is a valid IPv4 or IPv6 address and classify it.
whois_lookupWHOIS via RDAP for a domain (registrar, created/expiry dates, status, nameservers, DNSSEC), an IP address (network name, range, owner org, country, abuse contact) or an ASN like AS…Reads private dataNo findings
Why it is in this group
- The name "whois_lookup" says "lookup": a word for reading.
What it can reach
- private-dataThe description's first sentence says "contact": it reads contacts.
Description, as the server wrote it WHOIS via RDAP for a domain (registrar, created/expiry dates, status, nameservers, DNSSEC), an IP address (network name, range, owner org, country, abuse contact) or an ASN like AS13335.
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.
64 paths in this server alone from private data, through text someone else wrote, to a way out. Denying 4 outbound tools breaks every one.
- Reads private data4
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write4
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out4
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
{
"permissions": {
"deny": [
"mcp__ip__check_website_legit",
"mcp__ip__check_website_status",
"mcp__ip__convert_timezone",
"mcp__ip__trace_redirects"
]
}
}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, 18:38 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
- 18
- 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 18 tools that change things (1 irreversible, 17 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://www.ferntool.com/mcp: tools/list returned 30 tools to an anonymous client, including convert_timezone (irreversible), reverse_dns (write), subnet_mask_convert (write), subnet_calc (write), ipv6_plan_networks (write) and 13 more
Posture changes
- Nov 20, 2026
- Tools that change things, listed without credentials: 15 to 18
- Nov 13, 2026
- Tools that change things, listed without credentials: 14 to 15
- Oct 29, 2026
- Tools that change things, listed without credentials: 10 to 14
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: 15 -> 18.View diff
- Tools that change things, listed without credentials: 15 to 18
PostureRemote posture changed. Tools that change things, listed without credentials: 14 -> 15.View diff
- Tools that change things, listed without credentials: 14 to 15
Tools1 added, 1 changed.+1 added~1 changedView diff
- Added:analyze_email_headersOnly reads
- Changed:subnet_calcChanges thingsdescriptioninputSchema
PostureRemote posture changed. Tools that change things, listed without credentials: 10 -> 14.View diff
- Tools that change things, listed without credentials: 10 to 14
Tools6 added.+6 addedView diff
- Added:check_dns_propagationChanges things
- Added:check_email_securityChanges things
- Added:check_website_legitChanges things
- Added:check_website_statusOnly reads
- Added:generate_spf_recordChanges things
- Added:trace_redirectsChanges things
Install
Pinned to version 1.2.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http ip https://www.ferntool.com/mcpclaude mcp add --transport http ip https://www.ferntool.com/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__ip__get_my_ip",
"mcp__ip__lookup_ip",
"mcp__ip__validate_ip",
"mcp__ip__batch_lookup_ip",
"mcp__ip__whois_lookup",
"mcp__ip__dns_lookup",
"mcp__ip__count_words",
"mcp__ip__get_current_time",
"mcp__ip__analyze_email_headers",
"mcp__ip__ai_service_status"
],
"ask": [
"mcp__ip__reverse_dns",
"mcp__ip__subnet_calc",
"mcp__ip__estimate_ai_cost",
"mcp__ip__make_qr_code",
"mcp__ip__convert_timestamp",
"mcp__ip__date_calc",
"mcp__ip__convert_timezone",
"mcp__ip__random_number",
"mcp__ip__pick_random",
"mcp__ip__check_dns_propagation",
"mcp__ip__check_email_security",
"mcp__ip__check_website_status",
"mcp__ip__trace_redirects",
"mcp__ip__check_website_legit",
"mcp__ip__generate_spf_record"
],
"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 ip. Review it before you use it.
Capability tags behind 9 rules
- mcp__ip__lookup_ip private-data
- mcp__ip__whois_lookup private-data
- mcp__ip__dns_lookup untrusted-input
- mcp__ip__convert_timezone outbound
- mcp__ip__check_website_status untrusted-input, outbound
- mcp__ip__trace_redirects outbound
- mcp__ip__check_website_legit outbound
- mcp__ip__analyze_email_headers private-data, untrusted-input
- mcp__ip__ai_service_status private-data, untrusted-input
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/com.ferntool/ip/verify?hash=262678115359408cc2d2acee3a0f29cb4ceed15da06964d61e8bfad90f868b40" | jq -e '.changed == false'Pinned hash 262678115359, from Nov 9, 2026, 08:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.ferntool/ip/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.ferntool/ip)Source: MCP Registry. Synced Oct 26, 2026, 05:17 UTC.
FernTool Network Tools MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the FernTool Network Tools MCP server safe?
- No scan can promise that. What its definitions show: 25 tools, 14 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 FernTool Network Tools MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the FernTool Network Tools MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: convert_timezone.
What tools does the FernTool Network Tools MCP server have?
- 25 tools: 1 irreversible, 13 write, 11 read. convert_timezone, reverse_dns, subnet_calc, estimate_ai_cost, make_qr_code, convert_timestamp, date_calc, random_number and 17 more.
Does the FernTool Network Tools MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the FernTool Network Tools MCP server send data to outside services?
- 4 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): convert_timezone, check_website_status, trace_redirects and check_website_legit.
Has the FernTool Network Tools MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 9, 2026. Every change is on this page and in its Atom feed.