# `io.github.paperandbeyond23-gif/propzapi` 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/io.github.paperandbeyond23-gif/propzapi
- JSON: https://anlyon.dev/api/v1/servers/io.github.paperandbeyond23-gif/propzapi
- Version: 0.3.1 (active)
- Publisher: io.github.paperandbeyond23-gif (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/paperandbeyond23-gif/propzapi-skills
- Metadata from the official MCP Registry, synced 2026-10-21T18:43:15.896Z

Title and description, as the publisher wrote them:

```untrusted-server-text
Render-and-verify API: HTML/CSS to image or PDF, screenshot any URL, confirm the text rendered.
```

Scanned 2026-10-21T19:25:57.596Z over streamable-http.

**3 tools: 1 change things and 2 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 | 2 | 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__propzapi__screenshot_url` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__propzapi__screenshot_url` |

## Findings

No check matched anything in these tool definitions.


## Changes things (1)

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

### `generate_image`

- The name "generate_image" says "generate": a word for a change.

Description, as the server wrote it:

```untrusted-server-text
Render an on-brand image from a template and your data, and return the image. Use list_templates first to see template ids and their variables. 1 credit per image; cost returned in _meta.
```

## Only reads (2)

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

### `list_templates`

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

Description, as the server wrote it:

```untrusted-server-text
List the image templates you can render, with the variables each accepts. Free.
```

### `screenshot_url`

- The name "screenshot_url" says "screenshot": a word for reading.
- Tag untrusted-input: The name "screenshot_url" says "screenshot" and "url": it reads web pages, which anyone can write. 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 any public web page and return the image. 1 credit; cost in _meta.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [
      "mcp__propzapi__list_templates"
    ],
    "ask": [
      "mcp__propzapi__generate_image",
      "mcp__propzapi__screenshot_url"
    ],
    "deny": []
  }
}
```

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

- `mcp__propzapi__screenshot_url`: untrusted-input, outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-10-22T15:03:49.567Z, unchanged since 2026-10-22T15:03:49.567Z. 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 | `2024-11-05` |
| WWW-Authenticate on 401 | `not observed` |
| resource_metadata in WWW-Authenticate | `none` |
| RFC 9728 protected resource metadata | `https://api.propzapi.com/.well-known/oauth-protected-resource/mcp` |
| Authorization servers | `https://api.propzapi.com` |
| Legacy HTTP+SSE transport | `no` |
| Dynamic client registration | `yes` |
| Client ID metadata documents | `no` |

- **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://api.propzapi.com/mcp: tools/list returned 3 tools to an anonymous client, including generate_image (write)
```