# Extract page content

Extract clean content from up to 5 URLs in one call. Needs urls. Served by Tavily MCP.

Extract clean content from up to 5 URLs in one call, served through Tavily's hosted MCP server. 1 credit per batch of 5 successful extractions in basic depth, 2 in advanced; nothing billed when no page could be extracted. Proof of the MCP bridge: same billing rules as any HTTP tool.

- Tool ID: `tavily-mcp/extract`
- Name in the catalog: Extract page content (via Tavily MCP)
- Provider: [Tavily MCP](/providers/tavily-mcp.md)
- Capability: [Page to markdown](/tools/web-scraping/scrape.md)
- Price: from $0.008 per 5 results
- Authentication: an authorised Agentik workspace is required for execution, including zero-price tools.

## Pricing contract

The provider’s price, with no markup. Billed for measured usage.


```json
{
  "model": "per_unit",
  "amountUsd": 0.008,
  "unitsPath": "results",
  "unitsPer": 5,
  "maxUnits": 1,
  "unitsFallback": 1,
  "multipliers": [
    {
      "when": {
        "field": "extract_depth",
        "equals": "advanced"
      },
      "factor": 2
    }
  ]
}
```

Pricing source: [https://docs.tavily.com/documentation/api-credits](https://docs.tavily.com/documentation/api-credits). Extract: 1 credit per 5 successful URLs in basic depth, 2 in advanced; pay-as-you-go $0.008 per credit..

Price verification date: 2026-10-08.

## Complete input schema


```json
{
  "type": "object",
  "properties": {
    "urls": {
      "description": "List of URLs to extract content from",
      "items": {
        "type": "string"
      },
      "type": "array",
      "maxItems": 5
    },
    "extract_depth": {
      "default": "basic",
      "description": "Use 'advanced' for LinkedIn, protected sites, or tables/embedded content",
      "enum": [
        "basic",
        "advanced"
      ],
      "type": "string"
    },
    "include_images": {
      "default": false,
      "description": "Include images from pages",
      "type": "boolean"
    },
    "format": {
      "default": "markdown",
      "description": "Output format",
      "enum": [
        "markdown",
        "text"
      ],
      "type": "string"
    },
    "include_favicon": {
      "default": false,
      "description": "Include favicon URLs",
      "type": "boolean"
    },
    "query": {
      "default": "",
      "description": "Query to rerank content chunks by relevance",
      "type": "string"
    }
  },
  "required": [
    "urls"
  ],
  "additionalProperties": false
}
```

## Published example

This is the provider tool’s published example. Replace example values with the user’s requested inputs, respecting the schema; do not execute an example merely to test a connection.


```json
{
  "tool_id": "tavily-mcp/extract",
  "input": {
    "urls": [
      "https://example.com"
    ]
  }
}
```

## Execute and retrieve

Inspect again before execution, explain the price and obtain the required authority. Use MCP run_tool or POST /v1/run with this tool ID, valid input and an idempotency key. Save the returned run ID and follow the actual state. If Agentik answers that the tool is temporarily unavailable, do not retry it blindly; use discovery to propose an alternative.

A partial or uncertain result can still have consumed provider resources. Consult [billing](/docs/billing.md), [idempotency](/docs/idempotency.md) and [asynchronous results](/docs/async.md).

[Provider documentation](https://docs.tavily.com/documentation/mcp)

[REST inspection](https://api.agentik.cc/v1/tools/tavily-mcp/extract) · [OpenAPI](/openapi.json) · [Connection guide](/connect.md)

---

[HTML page](/providers/tavily-mcp/extract) · [Agent index](/llms.txt)