extract
ActiveTool of Anybrowse
Extract structured data from any URL as JSON. Provide a schema describing what fields you want. Schema format: {"fieldName": "type"} where type is one of: string, number, boolean, array, object. Example: {"title": "string", "price": "number", "inStock": "boolean"}. Great for prices, availability, product details, contact info.
Parameters schema
{
"type": "object",
"required": [
"url",
"schema"
],
"properties": {
"url": {
"type": "string",
"description": "The URL to extract data from"
},
"schema": {
"type": "object",
"description": "Field names mapped to type strings. Format: {\"fieldName\": \"string|number|boolean|array|object\"}. Example: {\"title\": \"string\", \"price\": \"number\", \"inStock\": \"boolean\", \"tags\": \"array\"}",
"additionalProperties": {
"enum": [
"string",
"number",
"boolean",
"array",
"object"
],
"type": "string"
}
},
"context": {
"type": "string",
"description": "Optional: what you're trying to accomplish (helps LLM extraction accuracy)"
}
}
}No endpoints wrapped at confidence ≥ 0.70.
Parent server
Anybrowse
https://github.com/kc23go/anybrowse
2/7 registries