Extract Structured Data
extractFetch a web page and convert it into JSON using your own model via MCP sampling; supply a prompt and optional JSON Schema to shape the result.
Instructions
Fetch a page and turn it into JSON using your own model via MCP sampling (no extra Bright Data cost beyond the page fetch). Pass extraction_prompt and optionally a JSON Schema in schema to shape the output.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"url": "<url>"
},
"name": "extract"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | ||
| fresh | No | Bypass the response cache and fetch again (costs a request) | |
| schema | No | Optional JSON Schema the output must follow | |
| country | No | 2-letter country code to route the request through (e.g. "us", "de") | |
| extraction_prompt | No | What to extract |