tld.expert MCP server
expert.tld/tld-experttld.expertstreamable-httpv1.0.0Scanned
Live domain availability, TLD alternatives, dated registrar prices and expert TLD advice.
5 tools: 3 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 3
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- 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 tld.expert MCP server can do
The tld.expert MCP server is published by tld.expert, a domain the MCP Registry verified. It has 5 tools. It can create or change data (3 tools: check_domain_availability, suggest_tld_alternatives and check_brand_name), but cannot delete data. 2 tools only read.
3 tools bring in text other people can write (check_domain_availability, suggest_tld_alternatives and check_brand_name).
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 15, 2026, version 1.0.0.
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.
5 tools
Changes things 3Claude Code: ask
check_brand_nameUse this when the user is naming a product or company and asks whether the name is free beyond the domain: a GitHub account or org, an npm package, or a US trademark ("is acme take…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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use this when the user is naming a product or company and asks whether the name is free beyond the domain: a GitHub account or org, an npm package, or a US trademark ("is acme taken on GitHub", "is there a trademark for acme"). Checks GitHub, the npm registry and live USPTO marks right now; each answer carries its source URL and checked time. "none" means the source has no record, never that the name is available or safe to use; a trademark search is not legal clearance. For the domain itself, call check_domain_availability.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
check_domain_availabilityUse this when the user wants to know if a domain name is available or taken, or asks "can I get <name>".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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use this when the user wants to know if a domain name is available or taken, or asks "can I get <name>". Accepts a full domain ("acme.io") for one verdict, or a bare name ("acme") to check it across popular TLDs (com, io, ai, co, app, dev, net, org, xyz) or a custom TLD list. Checks live DNS, registry RDAP/WHOIS and a registrar; never claims "available" without registrar confirmation. Returns a verdict per domain, buy links for names that may be free, and a tld.expert URL to cite. For one full domain that is taken, the result also carries registration: who it is registered with, when it expires, whether it is in redemption or pending delete, and whether it is listed for sale on a marketplace, from the registry's own RDAP/WHOIS. Use it for "who owns this domain", "when does it expire" and "is it for sale".
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
suggest_tld_alternativesUse this when the domain the user wants is taken (or they ask for other options for a name).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.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
What it can reach
- untrusted-inputThe server marks it openWorldHint: true: it reaches things outside the server's own data.
Description, as the server wrote it Use this when the domain the user wants is taken (or they ask for other options for a name). Given a full domain like "acme.com", proposes other endings (acme.io), added words (getacme.com), domain hacks and related words, checks every candidate live, and returns only the ones that are not taken. Slower than a single check (up to ~30 live lookups). Also use it when the user describes what the domain is for ("a fitness app in brazil", "a scratch site for side projects"): pass that as brief, with their name as domain if they have one. It then answers like the tld.expert search box: endings that fit the project (each with why and its source page), the popular endings, and name variants, every one checked live, taken ones counted but not listed. In brief mode, audience (who it is for) and vibe (how the name should feel) rethink the name ideas and lead with endings that suit them, like the questionnaire on the site. A suggestion on a gated ending (.law for licensed lawyers, .nyc for a New York City address) carries registration_rule with the registry source; closed ones are only proposed when the brief says the user qualifies.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: true
Only reads 2Show 2 read-only tools
explain_tldUse this when the user asks what a domain extension is, what it means, who runs it, who can register it, or whether it fits their project ("is .ai good for a startup", "what is .io…No findings
Why it is in this group
- The name "explain_tld" says "explain": a word for reading.
Description, as the server wrote it Use this when the user asks what a domain extension is, what it means, who runs it, who can register it, or whether it fits their project ("is .ai good for a startup", "what is .io", "does .web exist"). Returns tld.expert’s editorial verdict, pros and cons, registry, registration restrictions, the use cases it ranks for, and a typical price. Also answers for well-known non-existent TLDs like .eth or .web.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
get_tld_pricesUse this when the user asks what a domain extension costs, where it is cheapest, or what it renews at.No findings
Why it is in this group
- The name "get_tld_prices" says "get": a word for reading.
Description, as the server wrote it Use this when the user asks what a domain extension costs, where it is cheapest, or what it renews at. Returns dated first-year, renewal and transfer prices per registrar (Porkbun, Dynadot, Cloudflare, Namecheap where tracked), the cheapest direct buy, the wholesale floor, and a renewal-trap flag when the renewal is 2x+ the intro price. Prices are the TLD standard price, not premium names. Also answers "what does it cost over 5 years": true_cost gives each registrar's 1/3/5/10-year cost, the cheapest path per horizon (stay, or register at one and transfer after year one for gTLDs) and recent renewal price changes, each with source URL and checked date.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
- idempotentHint: true
- openWorldHint: false
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.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write3
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
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, 18:54 UTC, unchanged since Nov 6, 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
- 3
- 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
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://tld.expert/mcp: tools/list returned 5 tools to an anonymous client, including check_domain_availability (write), suggest_tld_alternatives (write), check_brand_name (write)
Posture changes
- Nov 6, 2026
- Tools that change things, listed without credentials: 2 to 3
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.
Tools2 changed.~2 changedView diff
- Changed:check_domain_availabilityChanges thingsdescription
- Changed:suggest_tld_alternativesChanges thingsdescription
PostureRemote posture changed. Tools that change things, listed without credentials: 2 -> 3.View diff
- Tools that change things, listed without credentials: 2 to 3
Tools1 added, 3 changed.+1 added~3 changedView diff
- Added:check_brand_nameChanges things
- Changed:check_domain_availabilityChanges thingsinputSchema
- Changed:get_tld_pricesOnly readsdescription
- Changed:suggest_tld_alternativesChanges thingsdescriptioninputSchema
Install
Pinned to version 1.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http tld-expert https://tld.expert/mcpclaude mcp add --transport http tld-expert https://tld.expert/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__tld-expert__get_tld_prices",
"mcp__tld-expert__explain_tld"
],
"ask": [
"mcp__tld-expert__check_domain_availability",
"mcp__tld-expert__suggest_tld_alternatives",
"mcp__tld-expert__check_brand_name"
],
"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 tld-expert. Review it before you use it.
Capability tags behind 3 rules
- mcp__tld-expert__check_domain_availability untrusted-input
- mcp__tld-expert__suggest_tld_alternatives untrusted-input
- mcp__tld-expert__check_brand_name 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/expert.tld/tld-expert/verify?hash=13438599dd0ffeb28f99c9ae508d77ffad9677e5a586aa0a6c21475b19cde1cd" | jq -e '.changed == false'Pinned hash 13438599dd0f, from Nov 15, 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/expert.tld/tld-expert/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/expert.tld/tld-expert)Source: MCP Registry. Synced Oct 21, 2026, 18:12 UTC.
tld.expert MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the tld.expert MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 3 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 tld.expert MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the tld.expert MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the tld.expert MCP server have?
- 5 tools: 3 write, 2 read. check_domain_availability, suggest_tld_alternatives, check_brand_name, get_tld_prices and explain_tld.
Does the tld.expert MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the tld.expert MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the tld.expert MCP server changed its tools?
- Yes, 2 times since Anlyon Radar started tracking it, most recently on Nov 15, 2026. Every change is on this page and in its Atom feed.