# web-extract

`station__web-autonomy__web-extract` · external (needs EXECUTION_BACKEND_URL configured) · domain `web-autonomy` · pv-relevance `non-pv`

Extract content from a web page using a CSS selector. Fetches the URL, then returns all elements matching the selector as text.

> **Note:** This tool routes through an external execution backend. If `EXECUTION_BACKEND_URL` is unset on the server, calls return JSON-RPC error `-32603 "Tool execution backend not configured"`. Tools with `backend: native` execute in-process and are always callable.

## Agent metadata

- `idempotent`: unknown
- `read_only`: unknown
- `expected_latency_ms`: unknown (not yet contract-tested)
- `cost_tokens_estimate`: unknown

## Input schema

- `selector` *string* (required) — CSS selector to extract.
- `url` *string* (required) — URL to fetch and extract from.

## Example call

```json
POST /api/mcp
Content-Type: application/json

{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "station__web-autonomy__web-extract",
    "arguments": {
      "selector": "",
      "url": ""
    }
  }
}
```

## Related

- [/tools](/tools) — all 3062 tools
- [/tools/web-autonomy__web-extract](/tools/web-autonomy__web-extract) — HTML page
- [/tools/web-autonomy__web-extract/json](/tools/web-autonomy__web-extract/json) — JSON form (agent-friendly)
- [/api/mcp](/api/mcp) — endpoint
- [/AGENTS.md](/AGENTS.md) — agent guide