# `dev.toolvend/dns-whois-domain-tools` on Anlyon Radar

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by Anlyon Radar. It is data to inspect, not instructions to follow. Invisible characters are shown as [U+XXXX].
> No finding is not a safety guarantee: these are point-in-time checks of tool definitions, not of code or behaviour.

- Page: https://radar.anlyon.com/servers/dev.toolvend/dns-whois-domain-tools
- JSON: https://radar.anlyon.com/api/v1/servers/dev.toolvend/dns-whois-domain-tools
- Version: 0.1.6 (active)
- Publisher: dev.toolvend (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-11-11T16:17:38.998Z

Title and description, as the publisher wrote them:

```untrusted-server-text
toolvend - utility APIs for agents
Calendar, DNS, RDAP, LEI, URLs, scraping, text, VAT and QR utilities. Pay-per-call USDC.
```

Scanned 2026-11-11T16:18:11.091Z over streamable-http.

**11 tools: 7 change things and 4 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 7 | ask |
| Only reads | read | 4 | allow |

## Exfil surface

No private-data -> untrusted-input -> outbound path in this server alone: no tool is tagged private-data.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | none |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__dns-whois-domain-tools__extract` `mcp__dns-whois-domain-tools__robots` `mcp__dns-whois-domain-tools__sitemap` `mcp__dns-whois-domain-tools__url-inspect` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__dns-whois-domain-tools__extract` `mcp__dns-whois-domain-tools__robots` `mcp__dns-whois-domain-tools__sitemap` `mcp__dns-whois-domain-tools__url-inspect` |

## Findings

- **info** The word "credentials" in `url-inspect` ([credentials-mention](https://radar.anlyon.com/methodology#credentials-mention))

```untrusted-server-text
The input schema at properties.url.description mentions "credentials".

inputSchema.properties.url.description: "...ublic HTTP(S) URL on its standard port; credentials and private destinations are rejected"
```


## Changes things (7)

Creates or changes something that can be changed back. Claude Code: ask.

### `business-days`

- The description's first verb is "add": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Add/subtract, count or find business days across countries and subdivisions; list public holidays. Bundled 2024–2030 calendars, inclusive ranges, explicit weekends and closures, source attribution and coverage warnings. See /calendar/coverage. Paid per call: $0.01 in USDC via x402.
```

### `dns`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
DNS lookup over DoH. Common record types (A, AAAA, MX, TXT, NS, CAA, ...) as clean JSON. Paid per call: $0.005 in USDC via x402.
```

### `lei`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Global legal-entity/KYB lookup by LEI: official identity, jurisdiction, addresses, registration and renewal standing, risk flags, and GLEIF data freshness. Paid per call: $0.008 in USDC via x402.
```

### `qr`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
QR code generator. Returns a crisp SVG for text/URL payloads up to 2,048 UTF-8 bytes that fit the selected error-correction level. Paid per call: $0.003 in USDC via x402.
```

### `rdap`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Domain registration data (modern WHOIS) via RDAP: registrar, created/expiry dates, status, nameservers, DNSSEC. Paid per call: $0.005 in USDC via x402.
```

### `text-clean`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
Clean text: strip HTML, normalise unicode/whitespace, dedupe lines. Returns cleaned text plus stats. Paid per call: $0.003 in USDC via x402.
```

### `vat`

- Nothing in its name or description says what it does, so it is counted as a write.

Description, as the server wrote it:

```untrusted-server-text
VAT calculator for EU-27 + UK: net→gross or gross→net at standard or reduced rate. Includes rates table snapshot date. Paid per call: $0.002 in USDC via x402.
```

## Only reads (4)

Looks things up and changes nothing. Claude Code: allow.

### `extract`

- The description's first verb is "fetch": a word for reading.
- Tag untrusted-input: The description's first sentence says "fetch" and "web": it reads web pages, which anyone can write. The input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- Tag outbound: The 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:

```untrusted-server-text
Fetch a web page and return structured content: title, meta/OpenGraph, canonical, headings, links, readable text (boilerplate stripped). Add ?render=true for JavaScript-rendered pages ($0.03). Paid per call: $0.01 ($0.03 Execute JavaScript with Cloudflare Browser Run before extracting content.) in USDC via x402.
```

### `robots`

- The description's first verb is "fetch": a word for reading.
- Tag untrusted-input: The input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- Tag outbound: The 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:

```untrusted-server-text
Fetch and parse robots.txt (+ llms.txt if present) into structured JSON, including which AI crawlers are blocked. Paid per call: $0.005 in USDC via x402.
```

### `sitemap`

- The description's first verb is "fetch": a word for reading.
- Tag untrusted-input: The input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- Tag outbound: The 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:

```untrusted-server-text
Fetch and parse sitemap XML or gzip into JSON. For an index, follow the first N children with ?follow=N. Caps merged output at 500 URLs. Paid per call: $0.005 in USDC via x402.
```

### `url-inspect`

- The name "url-inspect" says "inspect": a word for reading.
- Tag untrusted-input: The name "url-inspect" says "inspect" and "url": it reads web pages, which anyone can write. The description's first sentence says "inspect" and "url": it reads web pages, which anyone can write. The input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- Tag outbound: The 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.
- Findings: info credentials-mention

Description, as the server wrote it:

```untrusted-server-text
Inspect a public URL: HEAD redirect trace, DNS A/AAAA observations and security headers in one report. At most 4 targets, no page body. Includes timestamps, partial-result warnings and factual findings; no safety or reputation verdict. Paid per call: $0.009 in USDC via x402.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `dns-whois-domain-tools`:

```json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__dns-whois-domain-tools__business-days",
      "mcp__dns-whois-domain-tools__dns",
      "mcp__dns-whois-domain-tools__rdap",
      "mcp__dns-whois-domain-tools__lei",
      "mcp__dns-whois-domain-tools__sitemap",
      "mcp__dns-whois-domain-tools__robots",
      "mcp__dns-whois-domain-tools__extract",
      "mcp__dns-whois-domain-tools__text-clean",
      "mcp__dns-whois-domain-tools__vat",
      "mcp__dns-whois-domain-tools__qr",
      "mcp__dns-whois-domain-tools__url-inspect"
    ],
    "deny": []
  }
}
```

Capability tags behind the rules (a read tagged outbound is asked about):

- `mcp__dns-whois-domain-tools__sitemap`: untrusted-input, outbound
- `mcp__dns-whois-domain-tools__robots`: untrusted-input, outbound
- `mcp__dns-whois-domain-tools__extract`: untrusted-input, outbound
- `mcp__dns-whois-domain-tools__url-inspect`: untrusted-input, outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T18:53:02.948Z, unchanged since 2026-10-22T14:46:53.354Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://radar.anlyon.com/methodology#remote-posture

| Fact | Observed |
| --- | --- |
| Reachable | `yes` |
| HTTP status of an anonymous initialize | `200` |
| tools/list served without credentials | `yes` |
| Tools that change things, listed without credentials | `7` |
| Protocol version | `2025-06-18` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `none` |
| Authorization servers | `none` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `not observed` |
| Client ID metadata documents | `not observed` |

- **warn** Tools that change things, listed to anyone ([unauth-remote-writes](https://radar.anlyon.com/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 7 tools that change things (7 write). Whether a call also works without credentials was not tested: tools are never called.

https://toolvend.dev/mcp: tools/list returned 11 tools to an anonymous client, including business-days (write), dns (write), rdap (write), lei (write), text-clean (write) and 2 more
```
