# Use The Website Specification with your agent.

[The Website Specification](https://specification.website/) (`specification.website`) registers 5 WebMCP tools. 3 of 5 tools declares `readOnlyHint`, so an agent can invoke them through `tools.call`. The registry runs the tool in a fresh headless page on specification.website and returns untrusted site content.

This page mirrors the [WebMCP Registry](https://wmcp.ai/sites/specification.website) listing for `specification.website`, last live-checked by the registry at 2026-09-21T20:48:09.380Z. Run `ghostget webmcp sites.get --input '{"domain":"specification.website"}' --json` for the current schema; the listing can drift between checks.

## Use The Website Specification 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":"specification.website"}' --json
```

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

```
ghostget webmcp tools.call --input '{"domain":"specification.website","tool":"get_topic","input":"{}"}' --json
```

## Registered WebMCP tools

The Website Specification publishes 5 tools on specification.website; 3 declare `readOnlyHint`.

| Tool | What it does | Callable through Ghostget |
| --- | --- | --- |
| `get_topic` | Fetch the full Markdown for one spec page by its slug. Returns the rendered body with YAML frontmatter (title, status, sources). Use this after search_spec or list_topics to read the canonical guidance. | Callable read-only tool |
| `list_topics` | List spec topics, optionally filtered by category and/or status. Returns title, status, category, summary, and URL for each. Use this when the user wants the canonical list (e.g. "all required SEO topics"). | Callable read-only tool |
| `open_checklist` | Navigate the user to the full spec checklist page. Optionally jumps to a category section via URL hash. UI action — does not return data. | Listed for discovery; the registry allows read-only calls only |
| `open_search` | Open the on-page ⌘K search overlay so the user can search the spec interactively. Optionally pre-fills a query. UI action — does not return results; use search_spec for that. | Listed for discovery; the registry allows read-only calls only |
| `search_spec` | Search The Website Specification for matching topics. Returns ranked results with title, status, category, canonical URL, and a one-line summary. Use this when the user asks about a topic by keyword (e.g. "CSP", "alt text", "llms.txt"). | Callable read-only tool |

## 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 The Website Specification changes its tools.
- **No account needed.** These calls are credential-free registry reads. For tools that need a session on specification.website, browse the site itself or check back when the registry lists more tools.