# Use xSeek with your agent.

[xSeek](https://xseek.io/) (`xseek.io`) registers 4 WebMCP tools. xSeek lists 4 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/xseek.io) listing for `xseek.io`, last live-checked by the registry at 2026-09-23T05:21:36.296Z. Run `ghostget webmcp sites.get --input '{"domain":"xseek.io"}' --json` for the current schema; the listing can drift between checks.

## Use xSeek 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":"xseek.io"}' --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

xSeek publishes 4 tools on xseek.io; 0 declare `readOnlyHint`.

| Tool | What it does | Callable through Ghostget |
| --- | --- | --- |
| `agent_ready_scan` | Run an Agent-Ready scan on a public URL. Returns a readiness score plus per-check pass/fail breakdown (semantic HTML, schema markup, meta tags, content structure, accessibility for AI crawlers). Use this to check whether a page is well-stru | Listed for discovery; the registry allows read-only calls only |
| `contact_xseek` | Submit a contact request to the xSeek team — for sales questions, demo requests, partnership inquiries, or pricing follow-ups. Personal email domains (gmail.com excluded — yahoo, outlook, hotmail, etc.) are rejected; the user must provide a | Listed for discovery; the registry allows read-only calls only |
| `llms_txt_scan` | Inspect a site's llms.txt (the AI-equivalent of robots.txt for declaring what AI crawlers can use) and return a generated draft when none is present. Useful to diagnose why a brand isn't picked up by AI assistants, and to produce a ready-to | Listed for discovery; the registry allows read-only calls only |
| `robots_txt_scan` | Analyze a site's robots.txt for AI crawler access. Returns which AI bots (GPTBot, ClaudeBot, PerplexityBot, Google-Extended, etc.) are allowed vs blocked, plus any general rules affecting AI agents. Common diagnostic for "why am I not being | 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 xSeek changes its tools.
- **No account needed.** These calls are credential-free registry reads. For tools that need a session on xseek.io, browse the site itself or check back when the registry lists more tools.