Extract structured information from web pages using LLM capabilities. Supports both cloud AI and self-hosted LLM extraction. Best for: Extracting specific structured data like prices, names, details. Not recommended for: When you need the full content of a page (use scrape); when you're not looki...
AI agents call firecrawl_extract to retrieve information from Firecrawl Web Scraping Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
urls | array | — | List of URLs to extract information from |
prompt | string | — | Prompt for the LLM extraction |
schema | object | — | JSON schema for structured data extraction |
systemPrompt | string | — | System prompt for LLM extraction |
enableWebSearch | boolean | — | Enable web search for additional context |
includeSubdomains | boolean | — | Include subdomains in extraction |
allowExternalLinks | boolean | — | Allow extraction from external links |
Parameters from the server's own tool schema.
This tool performs read-only data extraction from web pages. It accepts URLs and extraction instructions (prompts/schemas) to parse content and return structured information. There are no side effects on the target systems, no data modification, no command execution, and no irreversible operations.
From the tool's definition Tool extracts structured information from web pages using LLM capabilities with custom prompts and schemas. It retrieves and parses data from specified URLs without modifying, deleting, or executing commands on target systems.
Documented attack patterns abuse exactly the kind of access firecrawl_extract gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Firecrawl Web Scraping Server, and nothing reaches the server without passing your rules. This is the rule we recommend for firecrawl_extract:
{
"version": "1",
"default": "deny",
"tools": {
"firecrawl_extract": {}
}
}firecrawl_extract is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Extract structured information from web pages using LLM capabilities. Supports both cloud AI and self-hosted LLM extraction. Best for: Extracting specific structured data like prices, names, details. Not recommended for: When you need the full content of a page (use scrape); when you're not looking for specific structured data. Arguments: - urls: Array of URLs to extract information from - prompt: Custom prompt for the LLM extraction - systemPrompt: System prompt to guide the LLM - schema: JSON schema for structured data extraction - allowExternalLinks: Allow extraction from external links - enableWebSearch: Enable web search for additional context - includeSubdomains: Include subdomains in extraction Prompt Example: "Extract the product name, price, and description from these product pages." Usage Example: json { "name": "firecrawl_extract", "arguments": { "urls": ["https://example.com/page1", "https://example.com/page2"], "prompt": "Extract product information including name, price, and description", "systemPrompt": "You are a helpful assistant that extracts product information", "schema": { "type": "object", "properties": { "name": { "type": "string" }, "price": { "type": "number" }, "description": { "type": "string" } }, "required": ["name", "price"] }, "allowExternalLinks": false, "enableWebSearch": false, "includeSubdomains": false } } Returns: Extracted structured data as defined by your schema. It is categorised as a Read tool in the Firecrawl Web Scraping Server MCP Server, which means it retrieves data without modifying state.
firecrawl_extract accepts 7 parameters: urls, prompt, schema, systemPrompt, enableWebSearch, includeSubdomains, allowExternalLinks. The full parameter table on this page comes from the server's own tool schema.
Register the Firecrawl Web Scraping Server MCP server in PolicyLayer and add a rule for firecrawl_extract: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Firecrawl Web Scraping Server. Nothing to install.
firecrawl_extract is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the firecrawl_extract rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for firecrawl_extract. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
firecrawl_extract is provided by the Firecrawl Web Scraping Server MCP server (0xzapata/firecrawl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Firecrawl Web Scraping Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
8 Firecrawl Web Scraping Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.