TLD Bench
REMOTE · TLDBENCH.COM
Domain prices for every TLD at the top registrars: renewals, N-year totals, history, availability.
Available components
Last scanned (23 hours ago)
Scores higher than 57% of remote servers
Reachable. Last reached 21 Nov 2026.
Category E-commerce
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security74
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability44
- 17% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Partial
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 2857 tokens (~190/item across 15 items; 10 tools + 5 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management50
- Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage98
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 94% of tool parameters carry a description.Partial
- Structured output schemas are declared (100% of tools); any adoption earns full credit.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.
- 7 Nov 26 +1
- Stability: unverified → 0.03 ▲ functional
- 6 Nov 26 65
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 21 Nov 2026 · Probed https://tldbench.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=tldbench.com | CN=YE1,O=Let's Encrypt,C=US | 5 Nov 2026 | 3 Feb 2027 | ECDSA 256 | ECDSA-SHA384 | 6d500e26d2a23bad690fb2cfc223312e6b7 |
| SANs: *.tldbench.com, tldbench.com | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of tldbench.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| com. | DS published | 19718 | 13 | Verified |
| tldbench.com. | No DS | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://tldbench.com/mcp | Verified | 200 | |
| http (plaintext) | http://tldbench.com/mcp | HTTPS enforced | 301 | https://tldbench.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
cheapest_registrar Cheapest registrar ~256
Use this when the user wants the single best place to buy (or transfer) one or more extensions for N years. Ranks by the total cost of ownership, not the first-year promotion; returns the winner with a year-by-year breakdown, three runners-up and caveats. Up to 20 extensions in one call.
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | ISO 4217 currency for prices (default USD); converted at the ECB's daily rate, disclosed in `fx` |
| exclude_registrars | array | – | registrar ids to leave out |
| include_limited_promos | boolean | – | count limited promotions (one per customer, first-time customers only) in totals and rankings; default false: they are listed and flagged promo_limited, but year 1 is priced at the regular price |
| include_resellers | boolean | – | include registrars whose prices are a reseller account's tier (pricing_tier reseller, e.g. eNom); default false |
| operation | string | – | start with a new registration (default) or a transfer in |
| tlds | array | yes | 1-20 extensions |
| years | integer | – | horizon for totals, 1-10 years (default 3) |
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | string | yes | when the newest price in this response was collected |
| currency | string | yes | ISO 4217 |
| fx | – | yes | How converted prices were converted; null when nothing needed converting. |
| operation | string | yes | – |
| results | array | yes | – |
| urls | object | yes | each extension's page on tldbench.com |
| years | integer | yes | – |
No examples provided.
check_availability Check availability ~275
Use this when the user asks whether specific domain names are free. Checks the registry (RDAP, WHOIS for some ccTLDs) after a DNS pre-check, with an honest unknown, and adds the cheapest registrar's price to own each free name. Up to 50 names in one call.
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | ISO 4217 currency for prices (default USD); converted at the ECB's daily rate, disclosed in `fx` |
| domains | array | yes | 1-50 full names (example.com, bücher.de) |
| include_limited_promos | boolean | – | count limited promotions (one per customer, first-time customers only) in totals and rankings; default false: they are listed and flagged promo_limited, but year 1 is priced at the regular price |
| include_resellers | boolean | – | include registrars whose prices are a reseller account's tier (pricing_tier reseller, e.g. eNom); default false |
| mode | string | – | fast: a DNS delegation is accepted as proof of registration; precise: always ask the registry (status codes, expiry) |
| with_prices | boolean | – | add the cheapest registrar's price for names that are free |
| years | integer | – | horizon for totals, 1-10 years (default 3) |
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | string | yes | when this answer was put together |
| currency | string | yes | ISO 4217 |
| notes | array | yes | – |
| results | array | yes | in the order asked |
| years | integer | yes | – |
No examples provided.
compare_tld_prices Compare prices for an extension ~293
Use this when the user asks what an extension costs or where it is cheapest. Returns every registrar's register, renew, transfer and restore prices for one TLD, ranked by the N-year cost of ownership (default 3 years), with each price's source and date.
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | ISO 4217 currency for prices (default USD); converted at the ECB's daily rate, disclosed in `fx` |
| include_limited_promos | boolean | – | count limited promotions (one per customer, first-time customers only) in totals and rankings; default false: they are listed and flagged promo_limited, but year 1 is priced at the regular price |
| include_resellers | boolean | – | include registrars whose prices are a reseller account's tier (pricing_tier reseller, e.g. eNom); default false |
| include_stale | boolean | – | include prices not confirmed for 3x their source's cadence (marked stale) |
| limit | integer | – | offers returned, cheapest first (default 20) |
| registrars | array | – | only these registrars |
| sort | string | – | rank by the N-year total (default), or by one price |
| tld | string | yes | an extension: com, .io, co.uk or рф |
| years | integer | – | horizon for totals, 1-10 years (default 3) |
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | string | yes | when the newest price in this response was collected |
| currency | string | yes | ISO 4217 |
| fx | – | yes | How converted prices were converted; null when nothing needed converting. |
| offers | array | yes | – |
| offers_total | integer | yes | offers before `limit` and `registrars` |
| sort | string | yes | – |
| stats | object | yes | – |
| tld | string | yes | – |
| url | string | yes | the page on tldbench.com with the full comparison |
| years | integer | yes | – |
No examples provided.
get_registrar Registrar profile ~90
Use this when the user asks about a registrar: its country, group, size (gTLD domains under management), how many extensions it sells, and how fresh our prices for it are. Accepts our id, its name or an IANA id.
| Name | Type | Req | Description |
|---|---|---|---|
| registrar | string | yes | a registrar's id (porkbun), name (Porkbun) or IANA id (1861) |
| Name | Type | Req | Description |
|---|---|---|---|
| registrar | object | yes | – |
| url | string | yes | the page on tldbench.com with the full comparison |
No examples provided.
get_tld Extension facts ~224
Use this when the user asks what an extension is, who runs it, or whether it fits: type (generic or country code), registry, brand TLD or not, DNSSEC, RDAP and WHOIS servers, minimum term, second levels, registry fees, and its price summary.
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | ISO 4217 currency for prices (default USD); converted at the ECB's daily rate, disclosed in `fx` |
| include_limited_promos | boolean | – | count limited promotions (one per customer, first-time customers only) in totals and rankings; default false: they are listed and flagged promo_limited, but year 1 is priced at the regular price |
| include_resellers | boolean | – | include registrars whose prices are a reseller account's tier (pricing_tier reseller, e.g. eNom); default false |
| tld | string | yes | an extension: com, .io, co.uk or рф |
| years | integer | – | horizon for totals, 1-10 years (default 3) |
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | string | yes | when the newest price in this response was collected |
| currency | string | yes | ISO 4217 |
| facts | object | yes | – |
| fx | – | yes | How converted prices were converted; null when nothing needed converting. |
| second_levels | array | yes | priced extensions under this root (co.uk, org.uk under uk) |
| tld | object | yes | – |
| url | string | yes | the page on tldbench.com with the full comparison |
| wholesale | array | yes | known registry fees, newest first |
| years | integer | yes | – |
No examples provided.
list_coupons Promotions and coupons ~191
Use this when the user asks for promo codes, coupons, deals or first-year discounts. Returns coupon codes as each registrar's own API or promotions page lists them (code, operation, extensions, discount, limits, end date, last seen at the source, an example price with the code), and running promotional prices anyone gets without a code. Codes are seen at the source, not tested at checkout; quote the list price and renewal too.
| Name | Type | Req | Description |
|---|---|---|---|
| active_only | boolean | – | false: also coupons that expired in the last 30 days |
| currency | string | – | ISO 4217 currency for prices (default USD); converted at the ECB's daily rate, disclosed in `fx` |
| limit | integer | – | – |
| operation | string | – | – |
| registrar | string | – | – |
| tld | string | – | an extension: com, .io, co.uk or рф |
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | string | yes | – |
| coupons | array | yes | coupon codes seen at the registrars' own sources, by registrar |
| currency | string | yes | ISO 4217 |
| fx | – | yes | How converted prices were converted; null when nothing needed converting. |
| note | string | yes | – |
| promotions | array | yes | running promotional prices, cheapest first |
No examples provided.
price_history Price history ~171
Use this when the user asks how an extension's prices have moved or whether a rise is coming. Returns each registrar's price periods (changes only) and the registry's announced wholesale changes.
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | ISO 4217 currency for prices (default USD); converted at the ECB's daily rate, disclosed in `fx` |
| operation | string | – | register (a new registration, year 1), renew (one more year), transfer (move in; usually adds a year), restore (redeem an expired domain in its redemption period) |
| registrar | string | – | one registrar's id |
| since | string | – | YYYY-MM-DD: only periods that end on or after it |
| tld | string | yes | an extension: com, .io, co.uk or рф |
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | string | yes | when the newest price in this response was collected |
| currency | string | yes | ISO 4217 |
| fx | – | yes | How converted prices were converted; null when nothing needed converting. |
| registry_events | array | yes | – |
| series | array | yes | – |
| tld | string | yes | – |
| url | string | yes | the page on tldbench.com with the full comparison |
No examples provided.
search_name_across_tlds Search a name across extensions ~285
Use this when the user has a name and wants to know which extensions are free and what each costs to own. Checks one label across up to 50 extensions (or a preset: popular, tech, cheap, country:<cc>) and sorts the free ones by total cost.
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | ISO 4217 currency for prices (default USD); converted at the ECB's daily rate, disclosed in `fx` |
| include_limited_promos | boolean | – | count limited promotions (one per customer, first-time customers only) in totals and rankings; default false: they are listed and flagged promo_limited, but year 1 is priced at the regular price |
| include_resellers | boolean | – | include registrars whose prices are a reseller account's tier (pricing_tier reseller, e.g. eNom); default false |
| max_renew_price | number | – | leave out extensions whose cheapest renewal is above this (in `currency`) |
| name | string | yes | the label, without an extension (acmeforge) |
| preset | string | – | popular (default), tech, cheap, or country:<cc> (country:de) |
| tlds | array | – | 1-50 extensions; default: the preset |
| years | integer | – | horizon for totals, 1-10 years (default 3) |
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | string | yes | – |
| currency | string | yes | ISO 4217 |
| name | string | yes | the label checked |
| notes | array | yes | – |
| results | array | yes | available first, cheapest to own first; then unknown; then taken and the rest |
| tlds | array | yes | – |
| years | integer | yes | – |
No examples provided.
suggest_names Check and price name ideas ~314
Use this when the user needs name ideas. Pass `candidates` from your own brainstorm and we check and price them; with only `keywords` we add simple prefixes, suffixes, TLD hacks and combinations. Returns only names that are available or unknown, cheapest first.
| Name | Type | Req | Description |
|---|---|---|---|
| candidates | array | – | your own ideas: labels (brewly) or full names (brewly.co); labels are tried with each of `tlds` |
| currency | string | – | ISO 4217 currency for prices (default USD); converted at the ECB's daily rate, disclosed in `fx` |
| include_limited_promos | boolean | – | count limited promotions (one per customer, first-time customers only) in totals and rankings; default false: they are listed and flagged promo_limited, but year 1 is priced at the regular price |
| include_resellers | boolean | – | include registrars whose prices are a reseller account's tier (pricing_tier reseller, e.g. eNom); default false |
| keywords | array | – | words to build names from with simple rules (prefixes, suffixes, TLD hacks, pairs) |
| limit | integer | – | names to check (each counts against the availability limit; default 20) |
| max_length | integer | – | longest label |
| max_renew_price | number | – | – |
| tlds | array | – | extensions to try (default com) |
| years | integer | – | horizon for totals, 1-10 years (default 3) |
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | string | yes | – |
| checked | integer | yes | – |
| currency | string | yes | ISO 4217 |
| generated | integer | yes | names made from the input before checking |
| notes | array | yes | – |
| suggestions | array | yes | only names that are available or unknown: available first, cheapest first |
| years | integer | yes | – |
No examples provided.
total_cost_of_ownership Total cost of ownership ~273
Use this when the user compares the long-run cost of several names or extensions, at one registrar or the cheapest. Applies minimum terms and regular renewals; with transfer_after_year it also finds the cheapest registrar to move to later. Up to 20 domains or extensions in one call.
| Name | Type | Req | Description |
|---|---|---|---|
| currency | string | – | ISO 4217 currency for prices (default USD); converted at the ECB's daily rate, disclosed in `fx` |
| domains | array | – | 1-20 domain names (their extensions are priced) |
| include_limited_promos | boolean | – | count limited promotions (one per customer, first-time customers only) in totals and rankings; default false: they are listed and flagged promo_limited, but year 1 is priced at the regular price |
| include_resellers | boolean | – | include registrars whose prices are a reseller account's tier (pricing_tier reseller, e.g. eNom); default false |
| registrar | string | – | price at this registrar; default: the cheapest to own |
| tlds | array | – | 1-20 extensions |
| transfer_after_year | integer | – | also price moving to the cheapest renewing registrar after this many years |
| years | integer | – | horizon for totals, 1-10 years (default 3) |
| Name | Type | Req | Description |
|---|---|---|---|
| as_of | string | yes | when the newest price in this response was collected |
| currency | string | yes | ISO 4217 |
| fx | – | yes | How converted prices were converted; null when nothing needed converting. |
| rows | array | yes | – |
| years | integer | yes | – |
No examples provided.
How do I install the TLD Bench MCP server?
TLD Bench is a hosted endpoint at https://tldbench.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · tldbench.com
claude mcp add --transport http com-tldbench-tldbench 'https://tldbench.com/mcp'
What is the TLD Bench MCP server?
TLD Bench is an MCP server listed in the public MCP registry as com.tldbench/tldbench. Domain prices for every TLD at the top registrars: renewals, N-year totals, history, availability. This page covers its hosted endpoint (https://tldbench.com/mcp).
Is the TLD Bench MCP server safe to use?
TLD Bench scores 72 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the TLD Bench MCP server expose?
TLD Bench exposes 10 tools: compare_tld_prices, cheapest_registrar, total_cost_of_ownership, check_availability, search_name_across_tlds, and 5 more. Their descriptions and schemas cost roughly 2,372 tokens of context every time the server is loaded.
Does the TLD Bench MCP server require authentication?
No. We connected to TLD Bench without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the TLD Bench MCP server still maintained?
TLD Bench is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the TLD Bench MCP server?
VerifyMCP ran 13 checks on TLD Bench, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.