# `io.github.zaffy18/agent-toolbox` 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/io.github.zaffy18/agent-toolbox
- JSON: https://radar.anlyon.com/api/v1/servers/io.github.zaffy18/agent-toolbox
- Version: 1.0.0 (active)
- Publisher: io.github.zaffy18 (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-24T14:18:02.424Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Agent Toolbox
Everyday tools for AI agents, paid per call with x402: images, markdown, speech-to-text, embeddings.
```

Scanned 2026-11-09T01:18:15.340Z over streamable-http.

**24 tools: 1 can delete or cancel things, 16 change things and 7 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 1 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 16 | ask |
| Only reads | read | 7 | allow |

## Exfil surface

294 private-data -> untrusted-input -> outbound paths in this server alone. Denying 2 private-data tools breaks every one: `mcp__agent-toolbox__url_to_markdown`, `mcp__agent-toolbox__watch_status`.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__agent-toolbox__url_to_markdown` `mcp__agent-toolbox__watch_status` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__agent-toolbox__chat_gpt_oss_120b` `mcp__agent-toolbox__chat_qwen3_30b` `mcp__agent-toolbox__company_lei` `mcp__agent-toolbox__company_search` `mcp__agent-toolbox__company_us` `mcp__agent-toolbox__dns_lookup` `mcp__agent-toolbox__domain_whois` `mcp__agent-toolbox__embed_text` `mcp__agent-toolbox__extract_data` `mcp__agent-toolbox__extract_free` `mcp__agent-toolbox__file_to_markdown` `mcp__agent-toolbox__fx_rates` `mcp__agent-toolbox__generate_image` `mcp__agent-toolbox__read_url` `mcp__agent-toolbox__screenshot` `mcp__agent-toolbox__summarize` `mcp__agent-toolbox__transcribe_audio` `mcp__agent-toolbox__translate_text` `mcp__agent-toolbox__url_to_markdown` `mcp__agent-toolbox__verify_email` `mcp__agent-toolbox__watch_field` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__agent-toolbox__extract_data` `mcp__agent-toolbox__extract_free` `mcp__agent-toolbox__read_url` `mcp__agent-toolbox__screenshot` `mcp__agent-toolbox__summarize` `mcp__agent-toolbox__url_to_markdown` `mcp__agent-toolbox__watch_field` |

| Private data | Untrusted input | Outbound |
| --- | --- | --- |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_gpt_oss_120b` | `mcp__agent-toolbox__extract_data` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_gpt_oss_120b` | `mcp__agent-toolbox__extract_free` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_gpt_oss_120b` | `mcp__agent-toolbox__read_url` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_gpt_oss_120b` | `mcp__agent-toolbox__screenshot` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_gpt_oss_120b` | `mcp__agent-toolbox__summarize` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_gpt_oss_120b` | `mcp__agent-toolbox__url_to_markdown` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_gpt_oss_120b` | `mcp__agent-toolbox__watch_field` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_qwen3_30b` | `mcp__agent-toolbox__extract_data` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_qwen3_30b` | `mcp__agent-toolbox__extract_free` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_qwen3_30b` | `mcp__agent-toolbox__read_url` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_qwen3_30b` | `mcp__agent-toolbox__screenshot` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_qwen3_30b` | `mcp__agent-toolbox__summarize` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_qwen3_30b` | `mcp__agent-toolbox__url_to_markdown` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__chat_qwen3_30b` | `mcp__agent-toolbox__watch_field` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_lei` | `mcp__agent-toolbox__extract_data` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_lei` | `mcp__agent-toolbox__extract_free` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_lei` | `mcp__agent-toolbox__read_url` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_lei` | `mcp__agent-toolbox__screenshot` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_lei` | `mcp__agent-toolbox__summarize` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_lei` | `mcp__agent-toolbox__url_to_markdown` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_lei` | `mcp__agent-toolbox__watch_field` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_search` | `mcp__agent-toolbox__extract_data` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_search` | `mcp__agent-toolbox__extract_free` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_search` | `mcp__agent-toolbox__read_url` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_search` | `mcp__agent-toolbox__screenshot` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_search` | `mcp__agent-toolbox__summarize` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_search` | `mcp__agent-toolbox__url_to_markdown` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_search` | `mcp__agent-toolbox__watch_field` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_us` | `mcp__agent-toolbox__extract_data` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_us` | `mcp__agent-toolbox__extract_free` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_us` | `mcp__agent-toolbox__read_url` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_us` | `mcp__agent-toolbox__screenshot` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_us` | `mcp__agent-toolbox__summarize` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_us` | `mcp__agent-toolbox__url_to_markdown` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__company_us` | `mcp__agent-toolbox__watch_field` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__dns_lookup` | `mcp__agent-toolbox__extract_data` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__dns_lookup` | `mcp__agent-toolbox__extract_free` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__dns_lookup` | `mcp__agent-toolbox__read_url` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__dns_lookup` | `mcp__agent-toolbox__screenshot` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__dns_lookup` | `mcp__agent-toolbox__summarize` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__dns_lookup` | `mcp__agent-toolbox__url_to_markdown` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__dns_lookup` | `mcp__agent-toolbox__watch_field` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__domain_whois` | `mcp__agent-toolbox__extract_data` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__domain_whois` | `mcp__agent-toolbox__extract_free` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__domain_whois` | `mcp__agent-toolbox__read_url` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__domain_whois` | `mcp__agent-toolbox__screenshot` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__domain_whois` | `mcp__agent-toolbox__summarize` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__domain_whois` | `mcp__agent-toolbox__url_to_markdown` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__domain_whois` | `mcp__agent-toolbox__watch_field` |
| `mcp__agent-toolbox__url_to_markdown` | `mcp__agent-toolbox__embed_text` | `mcp__agent-toolbox__extract_data` |

And 244 more: every combination of one tool from each row of the table above.

## Findings

- **warn** Annotations that disagree with the tool in `generate_image` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "generate_image" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The name "generate_image" says "generate": a word for a change.
```

- **warn** Annotations that disagree with the tool in `file_to_markdown` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "file_to_markdown" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "convert": a word for a change.
```

- **warn** Annotations that disagree with the tool in `chat_gpt_oss_120b` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "chat_gpt_oss_120b" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "open": a word for a change.
```

- **warn** Annotations that disagree with the tool in `chat_qwen3_30b` ([annotation-conflict](https://radar.anlyon.com/methodology#annotation-conflict))

```untrusted-server-text
The server marks "chat_qwen3_30b" read-only (readOnlyHint: true), and its own name, description or input give the class "write".

annotations: {"readOnlyHint":true,"destructiveHint":false,"idempotentHint":false,"openWorldHint":true}; The description's first verb is "open": a word for a change.
```


## Deletes or cancels (1)

Removes, cancels or revokes something. Claude Code: deny.

### `stop_watch`

- The name "stop_watch" says "stop": a word for a change.
- The server marks it destructive (destructiveHint: true).

Description, as the server wrote it:

```untrusted-server-text
Free. Stop a field watch, with the watch_id and secret that watch_field returned.
```

## Changes things (16)

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

### `chat_gpt_oss_120b`

- The description's first verb is "open": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
OpenAI-compatible chat completion with gpt-oss-120b (OpenAI's open-weight reasoning model): set the base URL to /v1/llm/gpt-oss-120b in any OpenAI SDK. Up to 32,000 characters in and 2,048 tokens out per call, a fixed price per call, no streaming. Costs USD 0.005 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `chat_qwen3_30b`

- The description's first verb is "open": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
OpenAI-compatible chat completion with Qwen3 30B (fast mixture-of-experts model): set the base URL to /v1/llm/qwen3-30b in any OpenAI SDK. Up to 32,000 characters in and 2,048 tokens out per call, a fixed price per call, no streaming. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `company_lei`

- 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.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Full official record of a legal entity by its LEI (Legal Entity Identifier) from GLEIF: legal and other names, registered and head-office addresses, company-register number, legal form, status, founding date, LEI status, and its direct and ultimate parent companies. Costs USD 0.005 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `company_us`

- 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.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
US public company profile from SEC EDGAR by ticker or CIK: industry, exchange, state of incorporation, fiscal year end, address and phone, shares outstanding, latest full-year financials (revenue, net income, assets, liabilities, equity, cash, diluted EPS) and links to the latest 10-K, 10-Q and 8-K filings. Costs USD 0.01 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `domain_whois`

- 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.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Domain registration data from RDAP (the successor of WHOIS): registrar, creation, expiry and update dates, status codes, nameservers and DNSSEC. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `embed_text`

- 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.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Text embeddings with BGE-M3 (multilingual, 1024 dimensions) for search, clustering and RAG: up to 100 texts of up to 8,000 characters per call. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `extract_data`

- 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.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

Description, as the server wrote it:

```untrusted-server-text
Extract structured JSON from a web page, PDF or text: name the fields you want (up to 25, with types) and get each value with the exact quote from the page that states it. Every quote is checked against the page itself (verified, quoted, unverified or not_found), so values are never invented. Charged only when at least one field is found. Costs USD 0.005 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `extract_free`

- 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.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

Description, as the server wrote it:

```untrusted-server-text
Free. Extract structured JSON from a web page or text with a checked quote per field (up to 8 fields, Qwen3), 20 a day per IP. extract_data is the paid version: gpt-oss-120b, up to 25 fields, no limit.
```

### `file_to_markdown`

- The description's first verb is "convert": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Convert an uploaded document (PDF, Word, Excel, CSV, HTML, XML, OpenDocument; up to 10 MB) to Markdown. Costs USD 0.003 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `fx_rates`

- 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.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Currency exchange rates and conversion for about 30 currencies (USD, EUR, GBP, INR, JPY, CNY ...) from the European Central Bank reference rates of the latest working day. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `generate_image`

- The name "generate_image" says "generate": a word for a change.
- The server marks it read-only (readOnlyHint: true), but an annotation never lowers a class.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Generate a 1024x1024 JPEG image from a text prompt with FLUX.1 schnell; every prompt passes a safety check first (sexual content and other unsafe requests are refused and not charged). Returns the image as base64. Costs USD 0.01 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `service_info`

- 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.

Description, as the server wrote it:

```untrusted-server-text
Free. Lists every tool with its price and explains how payment works (x402 over MCP, USDC on Base).
```

### `transcribe_audio`

- 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.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Speech to text with Whisper large v3 turbo: transcribe audio (mp3, wav, m4a, ogg, webm; up to 20 MB, about 20 minutes) from a URL or base64, or translate the speech into English. Returns the text, language, duration and timed segments. Costs USD 0.01 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `translate_text`

- 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.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Translate text (up to 5,000 characters) between 100 languages with M2M100 1.2B. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `verify_email`

- 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.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Check an email address: format, whether the domain exists and accepts mail (MX records), disposable providers, role accounts and free providers, with a valid / risky / invalid verdict. The mailbox itself is not probed. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `watch_field`

- Nothing in its name or description says what it does, so it is counted as a write.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.
- Tag outbound: The input takes a URL (input.url): a request to a URL can carry data to whoever runs it.

Description, as the server wrote it:

```untrusted-server-text
Watch one field on a web page for 30 days, e.g. a price, stock status or version number: it is read again every 15 to 1440 minutes and an alert goes to your webhook, Slack, Discord or Telegram when it changes, goes below or above a number, contains a text, or disappears. Returns the current value now; check status or stop it for free with the watch secret. Costs USD 0.10 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

## Only reads (7)

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

### `company_search`

- The name "company_search" says "search": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data.

Description, as the server wrote it:

```untrusted-server-text
Find companies worldwide by name in the official GLEIF register of legal entities: legal name, LEI, country, registered address, company-register number, legal form and status, best match first, plus matching US-listed companies with ticker and SEC CIK. Costs USD 0.005 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `dns_lookup`

- The name "dns_lookup" says "lookup": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The description's first sentence says "http": it reads web pages, which anyone can write.

Description, as the server wrote it:

```untrusted-server-text
DNS records of a domain (A, AAAA, MX, TXT, NS, CNAME, SOA, CAA, SRV, PTR) over DNS-over-HTTPS (1.1.1.1), with DNSSEC validation status. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `read_url`

- The name "read_url" says "read": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The name "read_url" says "read" 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.

Description, as the server wrote it:

```untrusted-server-text
Free. Read a public web page or document (HTML, PDF, Word, Excel, CSV; up to 5 MB) as clean Markdown with its title. Up to 20 reads a minute per IP; for more, url_to_markdown is the paid version with no limit.
```

### `screenshot`

- The name "screenshot" says "screenshot": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The description's first sentence says "screenshot" 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
Screenshot of a public web page in a real headless Chrome after it has loaded (JavaScript included): a JPEG of the visible window or the full page, 320 to 1920 pixels wide, as base64. Costs USD 0.003 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `summarize`

- The name "summarize" says "summarize": a word for reading.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The description's first sentence says "summarize" 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
Summarize text (up to 60,000 characters) or a public web page or PDF by URL with Llama 3.1 8B, short, medium or long, optionally focused on a topic. Costs USD 0.003 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `url_to_markdown`

- The description's first verb is "fetch": a word for reading.
- Tag private-data: The description's first sentence says "fetch" and "document": it reads documents.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The name "url_to_markdown" says "url": it reads web pages, which anyone can write. 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 public web page or document (HTML, PDF, Word, Excel, CSV, XML; up to 10 MB) and return it as clean Markdown with its title and final URL. Add render=true for pages that build their content with JavaScript: they are opened in a real headless Chrome first. Costs USD 0.002 per call, paid with x402 (USDC on Base); calls that fail are not charged.
```

### `watch_status`

- The name "watch_status" says "status": a word for reading.
- Tag private-data: The input names a secret (input.secret), and the tool reads: it reads secrets.

Description, as the server wrote it:

```untrusted-server-text
Free. A field watch's status, current value and last 20 alerts, with the watch_id and secret that watch_field returned.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `agent-toolbox`:

```json
{
  "permissions": {
    "allow": [
      "mcp__agent-toolbox__dns_lookup",
      "mcp__agent-toolbox__company_search",
      "mcp__agent-toolbox__watch_status"
    ],
    "ask": [
      "mcp__agent-toolbox__generate_image",
      "mcp__agent-toolbox__url_to_markdown",
      "mcp__agent-toolbox__file_to_markdown",
      "mcp__agent-toolbox__transcribe_audio",
      "mcp__agent-toolbox__embed_text",
      "mcp__agent-toolbox__translate_text",
      "mcp__agent-toolbox__summarize",
      "mcp__agent-toolbox__verify_email",
      "mcp__agent-toolbox__fx_rates",
      "mcp__agent-toolbox__chat_gpt_oss_120b",
      "mcp__agent-toolbox__chat_qwen3_30b",
      "mcp__agent-toolbox__domain_whois",
      "mcp__agent-toolbox__company_lei",
      "mcp__agent-toolbox__company_us",
      "mcp__agent-toolbox__extract_data",
      "mcp__agent-toolbox__screenshot",
      "mcp__agent-toolbox__watch_field",
      "mcp__agent-toolbox__read_url",
      "mcp__agent-toolbox__extract_free",
      "mcp__agent-toolbox__service_info"
    ],
    "deny": [
      "mcp__agent-toolbox__stop_watch"
    ]
  }
}
```

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

- `mcp__agent-toolbox__generate_image`: untrusted-input
- `mcp__agent-toolbox__url_to_markdown`: private-data, untrusted-input, outbound
- `mcp__agent-toolbox__file_to_markdown`: untrusted-input
- `mcp__agent-toolbox__transcribe_audio`: untrusted-input
- `mcp__agent-toolbox__embed_text`: untrusted-input
- `mcp__agent-toolbox__translate_text`: untrusted-input
- `mcp__agent-toolbox__summarize`: untrusted-input, outbound
- `mcp__agent-toolbox__verify_email`: untrusted-input
- `mcp__agent-toolbox__fx_rates`: untrusted-input
- `mcp__agent-toolbox__dns_lookup`: untrusted-input
- `mcp__agent-toolbox__chat_gpt_oss_120b`: untrusted-input
- `mcp__agent-toolbox__chat_qwen3_30b`: untrusted-input
- `mcp__agent-toolbox__domain_whois`: untrusted-input
- `mcp__agent-toolbox__company_search`: untrusted-input
- `mcp__agent-toolbox__company_lei`: untrusted-input
- `mcp__agent-toolbox__company_us`: untrusted-input
- `mcp__agent-toolbox__extract_data`: untrusted-input, outbound
- `mcp__agent-toolbox__screenshot`: untrusted-input, outbound
- `mcp__agent-toolbox__watch_field`: untrusted-input, outbound
- `mcp__agent-toolbox__read_url`: untrusted-input, outbound
- `mcp__agent-toolbox__extract_free`: untrusted-input, outbound
- `mcp__agent-toolbox__watch_status`: private-data

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-15T13:23:00.427Z, unchanged since 2026-10-31T23:20:58.915Z. 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 | `17` |
| 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` |

- **high** 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 17 tools that change things (1 destructive, 16 write). Whether a call also works without credentials was not tested: tools are never called.

https://agent-toolbox.zafermemon87.workers.dev/mcp: tools/list returned 24 tools to an anonymous client, including stop_watch (destructive), generate_image (write), file_to_markdown (write), transcribe_audio (write), embed_text (write) and 12 more
```

Posture changes:

- 2026-10-31T23:20:58.915Z: Tools that change things, listed without credentials `11` -> `17`
