# `dev.cz-agents/sanctions` 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.cz-agents/sanctions
- JSON: https://radar.anlyon.com/api/v1/servers/dev.cz-agents/sanctions
- Version: 0.1.5 (active)
- Publisher: dev.cz-agents (domain proven to the MCP Registry)
- Runs: remote (streamable-http), local (npm)
- Sign-in to list tools: none
- Repository: https://github.com/martinhavel/cz-agents-mcp
- Metadata from the official MCP Registry, synced 2026-10-21T18:11:46.759Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Sanctions screening for KYC/AML — EU FSF + OFAC SDN checks for Czech companies & individuals.
```

Scanned 2026-11-17T12:18:48.653Z over streamable-http.

**6 tools: 2 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 | 2 | 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 or outbound.

| 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__sanctions__check_ico` `mcp__sanctions__get_listing` `mcp__sanctions__list_recent_updates` `mcp__sanctions__rescreen_portfolio` `mcp__sanctions__search_entity` `mcp__sanctions__search_person` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | none |

## Findings

No check matched anything in these tool definitions.


## Changes things (2)

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

### `check_ico`

- 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 whether a Czech IČO (or any company by IČO) appears on sanctions lists. Direct exact-ID lookup; pass `name` to also fuzzy-match if no direct hit.
```

### `rescreen_portfolio`

- 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
PAID. Re-screen your own list of subjects against sanctions-list changes since a given date. Answers "which of MY clients were affected", which list_recent_updates cannot: that tool returns the global change feed, this one intersects it with your portfolio. Requires payment via x402; call without payment first to receive the terms.
```

## Only reads (4)

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

### `get_listing`

- The name "get_listing" says "get": 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
Retrieve the full record for a single sanctions listing by its ID (format: `${source}:${source_list_id}`, e.g. "ofac:12345" or "eu:EU.123.789").
```

### `list_recent_updates`

- The name "list_recent_updates" says "list": 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
List sanctions added/removed/modified since a given date. Use for daily monitoring against a watchlist.
```

### `search_entity`

- The name "search_entity" 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
Fuzzy-search a sanctioned entity (company, organization) by name. Optional country narrows results.
```

### `search_person`

- The name "search_person" 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
Fuzzy-search a sanctioned person by name across all loaded lists. Optional date of birth and nationality narrow results. Returns matches with confidence scores (0-100). 100 = exact ID match, 80+ = strong fuzzy match, lower = review needed.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__sanctions__search_person",
      "mcp__sanctions__search_entity",
      "mcp__sanctions__get_listing",
      "mcp__sanctions__list_recent_updates"
    ],
    "ask": [
      "mcp__sanctions__check_ico",
      "mcp__sanctions__rescreen_portfolio"
    ],
    "deny": []
  }
}
```

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

- `mcp__sanctions__search_person`: untrusted-input
- `mcp__sanctions__search_entity`: untrusted-input
- `mcp__sanctions__check_ico`: untrusted-input
- `mcp__sanctions__get_listing`: untrusted-input
- `mcp__sanctions__list_recent_updates`: untrusted-input
- `mcp__sanctions__rescreen_portfolio`: untrusted-input

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-20T19:26:56.635Z, unchanged since 2026-10-22T15:21:23.258Z. 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 | `2` |
| 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

https://sanctions.cz-agents.dev/mcp: tools/list returned 6 tools to an anonymous client, including check_ico (write), rescreen_portfolio (write)
```
