get_markdown
Extract web content as markdown with filtering options including full content, optimized formatting, keyword search, or AI-powered extraction for specific information.
Instructions
[STATELESS] Extract content as markdown with filtering options. Supports: raw (full content), fit (optimized, default), bm25 (keyword search), llm (AI-powered extraction). Use bm25/llm with query for specific content. Creates new browser each time. For persistence use create_session + crawl.
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| cache | No | Cache-bust parameter (use different values to force fresh extraction) | 0 |
| filter | No | Filter type: raw (full), fit (optimized), bm25 (search), llm (AI extraction) | fit |
| query | No | Query string for bm25/llm filters. Required when using bm25 or llm filter. | |
| url | Yes | The URL to extract markdown from |
Input Schema (JSON Schema)
{
"properties": {
"cache": {
"default": "0",
"description": "Cache-bust parameter (use different values to force fresh extraction)",
"type": "string"
},
"filter": {
"default": "fit",
"description": "Filter type: raw (full), fit (optimized), bm25 (search), llm (AI extraction)",
"enum": [
"raw",
"fit",
"bm25",
"llm"
],
"type": "string"
},
"query": {
"description": "Query string for bm25/llm filters. Required when using bm25 or llm filter.",
"type": "string"
},
"url": {
"description": "The URL to extract markdown from",
"type": "string"
}
},
"required": [
"url"
],
"type": "object"
}