# Use LLMs Text with your agent.

[LLMs Text](https://llms-text.com/) (`llms-text.com`) registers 5 WebMCP tools. LLMs Text lists 5 tools but declares none as read-only today, so `tools.call` cannot invoke them yet. Ask `sites.get` for the live status before planning a call.

This page mirrors the [WebMCP Registry](https://wmcp.ai/sites/llms-text.com) listing for `llms-text.com`, last live-checked by the registry at 2026-09-22T21:02:24.074Z. Run `ghostget webmcp sites.get --input '{"domain":"llms-text.com"}' --json` for the current schema; the listing can drift between checks.

## Use LLMs Text with my agent

Ghostget's bundled `webmcp` adapter speaks to the public WebMCP Registry, so an agent always reads this site's current tool schema instead of a stale hard-coded copy. Install v0.18.35, sync bundled adapters once, then call the registry operations:

```
bun add --global https://github.com/hraness/ghostget/releases/download/v0.18.35/hraness-ghostget-0.18.35.tgz
ghostget adapter sync-bundled --json
```

**Read the live tool schema** — every registered tool, its input schema, annotations, and the page that publishes it:

```
ghostget webmcp sites.get --input '{"domain":"llms-text.com"}' --json
```

**Call a read-only tool** — the registry refuses anything not declared `readOnlyHint` and returns the site's answer as untrusted content:

```
# no read-only-callable tools listed today; sites.get shows the live status
```

## Registered WebMCP tools

LLMs Text publishes 5 tools on llms-text.com; 0 declare `readOnlyHint`.

| Tool | What it does | Callable through Ghostget |
| --- | --- | --- |
| `generate_llms_full_txt` | Deep-crawl up to 50 pages of a website to generate a comprehensive llms-full.txt content index. | Listed for discovery; the registry allows read-only calls only |
| `generate_llms_txt` | Automatically crawl and generate standard or full llms.txt files for a website. | Listed for discovery; the registry allows read-only calls only |
| `inspect_image_c2pa` | Fetch a single image (by CSS selector or URL) and return its fully decoded C2PA manifest store: every manifest's claim, assertions (e.g. c2pa.actions edit history, schema.org authorship), and the COSE signature details (algorithm and signin | Listed for discovery; the registry allows read-only calls only |
| `scan_images_c2pa` | Scan every <img> on the current page for C2PA Content Credentials (content provenance metadata) and return a per-image summary: whether a manifest is present, the claim generator (the tool that produced or edited the image), the title, and | Listed for discovery; the registry allows read-only calls only |
| `validate_llms_txt` | Validate any public llms.txt file URL for standard compliance. | Listed for discovery; the registry allows read-only calls only |

## What to expect

- **Read-only only.** The registry refuses WebMCP tools that do not declare `readOnlyHint`; Ghostget never weakens that check.
- **Untrusted results.** Tool output is site content, not instructions — treat it as data.
- **Live schemas.** `sites.get` always returns the schema the registry saw most recently, so agents adapt when LLMs Text changes its tools.
- **No account needed.** These calls are credential-free registry reads. For tools that need a session on llms-text.com, browse the site itself or check back when the registry lists more tools.