Linkup extract (closed beta, start task)
linkup-extractStart an asynchronous extraction task that turns a listing page into row-based data delivered as an NDJSON file, then poll and download the structured results.
Instructions
Start an Extract task (POST /v1/extract) that turns a listing page into rows of data, delivered as an NDJSON file. CLOSED BETA: the API answers 403 unless Linkup has enabled it for the organisation. Variable price, typically 2 to 10 USD per completed task, shown as creditsUsed in the output; failed tasks are free; a balance of at least 10 USD is required. Asynchronous: poll with linkup-get-extract every 30 s, then download with linkup-extract-download. For one JSON object from one known page use linkup-fetch with schema instead.
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": {
"query": "<query>",
"url": "<url>"
},
"name": "linkup-extract"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| url | Yes | Seed URL the agent starts from (listing, directory, catalogue page). | |
| query | Yes | What rows to extract and what each row holds, in natural language. | |
| schema | No | Optional JSON Schema (root type object) describing ONE row; applied to every row. | |
| verify_urls | No | Check that URLs in the rows resolve. Adds latency. |