Search the web and optionally extract content from search results. This is the most powerful web search tool available, and if available you should always default to using this tool for any web search needs. The query also supports search operators, that you can use if needed to refine the search...
AI agents call firecrawl_search to retrieve information from Firecrawl MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
firecrawl_search performs web searches and extracts content from results, which are fundamentally retrieval operations with no side effects. While it integrates with a web scraping service, the tool itself does not modify, delete, or execute arbitrary code—it only reads and returns data. The 'optionally extract content' phrasing refers to parsing and returning structured data, not creating or modifying it.
From the tool's definition Tool description states it "Search[es] the web and optionally extract[s] content from search results" with support for search operators. The verb 'search' and 'extract' indicate read-only operations that retrieve data without modification.
Attacks that exploit this kind of access
Search the web and optionally extract content from search results. This is the most powerful web search tool available, and if available you should always default to using this tool for any web search needs. The query also supports search operators, that you can use if needed to refine the search: | Operator | Functionality | Examples | ---|-|-| | \. It is categorised as a Read tool in the Firecrawl MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Firecrawl MCP Server MCP server in PolicyLayer and add a rule for firecrawl_search: 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 MCP Server. Nothing to install.
firecrawl_search 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_search 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_search. 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_search is provided by the Firecrawl MCP Server MCP server (jayceetran1995/firecrawl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →