Conduct deep web research on a query using intelligent crawling, search, and LLM analysis. Best for: Complex research questions requiring multiple sources, in-depth analysis. Not recommended for: Simple questions that can be answered with a single search; when you need very specific information f...
AI agents call firecrawl_deep_research 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 |
|---|---|---|---|
query | string | — | The query to research |
maxUrls | number | — | Maximum number of URLs to analyze (1-1000) |
maxDepth | number | — | Maximum depth of research iterations (1-10) |
timeLimit | number | — | Time limit in seconds (30-300) |
Parameters from the server's own tool schema.
This tool retrieves and analyzes web content through crawling and searching—pure information gathering with no side effects. It reads data from the web and processes it analytically, fitting the Read category. Severity is low because web scraping for research purposes poses minimal risk even if misused by an agent (e.g., querying excessive sources would be slow rather than harmful, and extraction is non-destructive).
From the tool's definition Tool performs 'deep web research', 'intelligent crawling, search, and LLM analysis' on a user-provided query.
Risk signalsAccepts freeform code/query input (query)
Documented attack patterns abuse exactly the kind of access firecrawl_deep_research 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_deep_research:
{
"version": "1",
"default": "deny",
"tools": {
"firecrawl_deep_research": {}
}
}firecrawl_deep_research 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.
Conduct deep web research on a query using intelligent crawling, search, and LLM analysis. Best for: Complex research questions requiring multiple sources, in-depth analysis. Not recommended for: Simple questions that can be answered with a single search; when you need very specific information from a known page (use scrape); when you need results quickly (deep research can take time). Arguments: - query (string, required): The research question or topic to explore. - maxDepth (number, optional): Maximum recursive depth for crawling/search (default: 3). - timeLimit (number, optional): Time limit in seconds for the research session (default: 120). - maxUrls (number, optional): Maximum number of URLs to analyze (default: 50). Prompt Example: "Research the environmental impact of electric vehicles versus gasoline vehicles." Usage Example: json { "name": "firecrawl_deep_research", "arguments": { "query": "What are the environmental impacts of electric vehicles compared to gasoline vehicles?", "maxDepth": 3, "timeLimit": 120, "maxUrls": 50 } } Returns: Final analysis generated by an LLM based on research. (data.finalAnalysis); may also include structured activities and sources used in the research process. It is categorised as a Read tool in the Firecrawl Web Scraping Server MCP Server, which means it retrieves data without modifying state.
firecrawl_deep_research accepts 4 parameters: query, maxUrls, maxDepth, timeLimit. 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_deep_research: 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_deep_research 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_deep_research 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_deep_research. 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_deep_research 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.