# `io.github.michaelvereb/llms-text` 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.michaelvereb/llms-text
- JSON: https://anlyon.dev/api/v1/servers/io.github.michaelvereb/llms-text
- Version: 1.0.2 (active)
- Publisher: io.github.michaelvereb (GitHub account)
- Runs: remote (streamable-http)
- Sign-in to list tools: none
- Repository: https://github.com/michaelvereb/vereb
- Metadata from the official MCP Registry, synced 2026-11-12T04:18:16.758Z

Title and description, as the publisher wrote them:

```untrusted-server-text
llms-text
Generate, validate, and deep-crawl /llms.txt and /llms-full.txt files for AI agents.
```

Scanned 2026-11-12T03:18:13.780Z over streamable-http.

**3 tools: 2 change things and 1 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 | 1 | 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__llms-text__generate_llms_full_txt` `mcp__llms-text__generate_llms_txt` `mcp__llms-text__validate_llms_txt` |
| outbound | Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL. | `mcp__llms-text__generate_llms_full_txt` `mcp__llms-text__generate_llms_txt` `mcp__llms-text__validate_llms_txt` |

## Findings

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

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

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

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

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

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


## Changes things (2)

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

### `generate_llms_full_txt`

- The name "generate_llms_full_txt" 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. The description's first sentence says "crawl": 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.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Deep-crawl up to 50 pages of a website to generate a comprehensive /llms-full.txt content index with full body markdown for AI agents. Generates full bundle immediately when session authorization is provided.
```

### `generate_llms_txt`

- The name "generate_llms_txt" 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. The description's first sentence says "crawl": 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.
- Findings: warn annotation-conflict

Description, as the server wrote it:

```untrusted-server-text
Automatically crawl any public website URL and generate a standard, token-efficient index-level /llms.txt file for AI agent context. 100% free with core page categorization, descriptions, and clean markdown.
```

## Only reads (1)

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

### `validate_llms_txt`

- The name "validate_llms_txt" says "validate": a word for reading.
- 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.
- Claude Code: ask, because it is tagged outbound.

Description, as the server wrote it:

```untrusted-server-text
Validate any public llms.txt or llms-full.txt file URL for standard compliance, missing H1, broken links, structure errors, and token count.
```

## Claude Code permissions

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

```json
{
  "permissions": {
    "allow": [],
    "ask": [
      "mcp__llms-text__generate_llms_txt",
      "mcp__llms-text__generate_llms_full_txt",
      "mcp__llms-text__validate_llms_txt"
    ],
    "deny": []
  }
}
```

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

- `mcp__llms-text__generate_llms_txt`: untrusted-input, outbound
- `mcp__llms-text__generate_llms_full_txt`: untrusted-input, outbound
- `mcp__llms-text__validate_llms_txt`: untrusted-input, outbound

## Remote posture

What an anonymous client saw at the remote endpoint, last 2026-11-12T10:20:01.209Z, unchanged since 2026-11-12T10:20:01.209Z. 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 | `2` |
| Protocol version | `2024-11-05` |
| 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 2 tools that change things (2 write). Whether a call also works without credentials was not tested: tools are never called.

https://www.llms-text.com/mcp: tools/list returned 3 tools to an anonymous client, including generate_llms_txt (write), generate_llms_full_txt (write)
```