Web Page Content Extraction
Metered
Tool ID: helve.web_extract
Fetch and extract clean markdown, summaries, or query-focused excerpts from up to 10 URLs across 9 extraction providers.
Input Parameters
| Parameter | Type | Required | Description |
urls | array | Required | The pages to extract, 1–20 absolute URLs. Providers that take one URL per call are fanned out by Helve. |
provider | string (exa | tavily | parallel | serper | firecrawl | linkup | valyu | jina | octen | auto) | Optional | Which provider fetches and cleans the pages. `auto` (default) picks the first configured provider in Helve's priority order. Brave and Perplexity have no extraction product. |
query | string | Optional | What you are extracting for. Drives focused excerpts and summaries on providers that support them (Exa, Tavily, Parallel, Firecrawl, Valyu). |
content | object | Optional | What to return for each URL. |
include_links | boolean | Optional | Return the page's outbound links in `links`. Native on Exa. |
include_images | boolean | Optional | Return the page's image URLs in `images`. Native on Exa and Tavily. |
max_age_hours | integer | Optional | Accept a cached copy up to this many hours old; 0 forces a live fetch. Native on Exa. |
timeout_ms | integer | Optional | Per-page fetch timeout in milliseconds, 1000–90000. Native on Exa and Tavily. |
strict | boolean | Optional | When true, any parameter the serving provider cannot honour is a 400 instead of a warning. Default false. |
provider_options | object | Optional | Escape hatch for provider-native parameters, keyed by provider id and merged into that provider's request unchanged. |
Call via REST API
curl -X POST https://helve.dev/v1/tools/call \
-H "Authorization: Bearer sk_live_YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"tool_id": "helve.web_extract",
"arguments": {
"urls": [
"https://helve.dev"
],
"provider": "auto"
}
}'
Call via MCP (call_tool)
{
"name": "call_tool",
"arguments": {
"tool_id": "helve.web_extract",
"arguments": {
"urls": [
"https://helve.dev"
],
"provider": "auto"
}
}
}
Related Web Extraction Tools