# `app.botnotice/mcp` on anlyon.dev

> Text inside fenced blocks marked untrusted-server-text was written by the MCP server's publisher, not by anlyon.dev. 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://anlyon.dev/servers/app.botnotice/mcp
- JSON: https://anlyon.dev/api/v1/servers/app.botnotice/mcp
- Version: 1.0.0 (active)
- Publisher: app.botnotice (domain proven to the MCP Registry)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Metadata from the official MCP Registry, synced 2026-10-21T17:44:10.375Z

Title and description, as the publisher wrote them:

```untrusted-server-text
AI disclosure laws by business and state, each law in full, and a website AI-notice check.
```

Scanned 2026-10-21T18:42:24.501Z over streamable-http.

**4 tools: 1 change things and 3 only read.**

| Group | Class | Tools | Claude Code |
| --- | --- | --- | --- |
| Deletes or cancels | destructive | 0 | deny |
| Can't be undone | irreversible | 0 | ask |
| Changes things | write | 1 | ask |
| Only reads | read | 3 | allow |

## Exfil surface

1 private-data -> untrusted-input -> outbound path in this server alone. Denying 1 outbound tool breaks every one: `mcp__botnotice__check_website`.

| Tag | Meaning | Tools |
| --- | --- | --- |
| private-data | Reads files, mail, messages, databases, secrets, calendars or repositories. | `mcp__botnotice__check_website` |
| untrusted-input | Brings in text someone else can write: web pages, inbound email, messages, issues and comments. | `mcp__botnotice__check_website` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__botnotice__check_website` |

| Private data | Untrusted input | Outbound |
| --- | --- | --- |
| `mcp__botnotice__check_website` | `mcp__botnotice__check_website` | `mcp__botnotice__check_website` |

## Findings

No check matched anything in these tool definitions.


## Changes things (1)

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

### `laws_for_business`

- 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
Given how a business uses AI and where its customers are, returns the laws in force and the ones coming, each with what must be disclosed, when, the penalties and the sources, plus the notice rules that satisfy all of them. Free, no account. Not legal advice.
```

## Only reads (3)

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

### `check_website`

- The description's first verb is "read": a word for reading.
- Tag private-data: The description's first sentence says "read" and "chat": it reads messages.
- Tag untrusted-input: The server marks it openWorldHint: true: it reaches things outside the server's own data. The name "check_website" says "website": it reads web pages, which anyone can write. The description's first sentence says "read" and "website": 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
Reads a public website: which chat or voice-AI tools it runs, whether an AI disclosure is already shown, and, for the business described, which laws that leaves unmet. The same check as the free scan at botnotice.app/scan, without the browser pass. Not legal advice.
```

### `get_law`

- The name "get_law" says "get": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
The full record for one law: who must comply, what to disclose, timing, duties, exemptions, penalties, enforcement, sources and the last-verified date. Slugs come from list_laws or the dataset at https://botnotice.app/datasets/ai-disclosure-laws.json.
```

### `list_laws`

- The name "list_laws" says "list": a word for reading.

Description, as the server wrote it:

```untrusted-server-text
Every AI disclosure law BotNotice tracks (U.S. states, federal, EU, UK), with status and effective date, optionally filtered. Also the pending bills.
```

## Claude Code permissions

For `.claude/settings.json`, assuming the server is installed as `botnotice`:

```json
{
  "permissions": {
    "allow": [
      "mcp__botnotice__get_law",
      "mcp__botnotice__list_laws"
    ],
    "ask": [
      "mcp__botnotice__laws_for_business",
      "mcp__botnotice__check_website"
    ],
    "deny": []
  }
}
```

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

- `mcp__botnotice__check_website`: private-data, untrusted-input, outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-10-22T14:22:18.120Z, unchanged since 2026-10-22T14:22:18.120Z. No credentials were sent and no tool was called. Values are shown as the endpoint returned them. Method: https://anlyon.dev/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 | `1` |
| 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://anlyon.dev/methodology#unauth-remote-writes))

```untrusted-server-text
The endpoint served tools/list without credentials, and the list has 1 tool that changes things (1 write). Whether a call also works without credentials was not tested: tools are never called.

https://botnotice.app/mcp: tools/list returned 4 tools to an anonymous client, including laws_for_business (write)
```