Crawl multiple web pages starting from seed URLs
AI agents call search.crawl to retrieve information from MCP Fullstack without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Web crawling is fundamentally a retrieval operation: it fetches and indexes publicly accessible or authorized content. No side effects, data modification, code execution, or financial transactions occur. The blast radius of misuse is limited to consuming bandwidth and potentially violating robots.txt policies, but no persistent damage or sensitive operations are enabled.
From the tool's definition Tool name is 'search.crawl' and description states 'Crawl multiple web pages starting from seed URLs' — this is a read-only operation that retrieves web content without modifying, deleting, or executing code on target systems.
Attacks that exploit this kind of access
Crawl multiple web pages starting from seed URLs. It is categorised as a Read tool in the MCP Fullstack MCP Server, which means it retrieves data without modifying state.
Register the MCP Fullstack MCP server in PolicyLayer and add a rule for search.crawl: 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 MCP Fullstack. Nothing to install.
search.crawl 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 search.crawl 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 search.crawl. 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.
search.crawl is provided by the MCP Fullstack MCP server (jacobfv/mcp-fullstack). 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 →