[STATELESS] Deep crawl a website following internal links. Use when: mapping entire sites, finding all pages, building comprehensive indexes. Control with max_depth (default 3) and max_pages (default 50). Note: May need JS execution for dynamic sites. Each page gets a fresh browser. For persisten...
AI agents invoke crawl_recursive to trigger actions in MCP Server for Crawl4AI. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool executes browser automation across potentially many pages (up to 50 by default), runs JavaScript, and performs networked operations against external sites at scale. It goes beyond simple read by spawning browser instances and executing JS, making it an Execute-category tool.
From the tool's definition Deep crawl a website following internal links... May need JS execution for dynamic sites. Each page gets a fresh browser.
Risk signalsBulk/mass operation — affects multiple targets
Documented attack patterns abuse exactly the kind of access crawl_recursive gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Server for Crawl4AI, and nothing reaches the server without passing your rules. This is the rule we recommend for crawl_recursive:
{
"version": "1",
"default": "deny",
"tools": {
"crawl_recursive": {
"limits": [
{
"counter": "crawl_recursive_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}crawl_recursive stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
[STATELESS] Deep crawl a website following internal links. Use when: mapping entire sites, finding all pages, building comprehensive indexes. Control with max_depth (default 3) and max_pages (default 50). Note: May need JS execution for dynamic sites. Each page gets a fresh browser. For persistent operations use create_session + crawl. It is categorised as a Execute tool in the MCP Server for Crawl4AI MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Server for Crawl4AI MCP server in PolicyLayer and add a rule for crawl_recursive: 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 Server for Crawl4AI. Nothing to install.
crawl_recursive is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the crawl_recursive 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 crawl_recursive. 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.
crawl_recursive is provided by the MCP Server for Crawl4AI MCP server (omgwtfwow/mcp-crawl4ai-ts). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Server for Crawl4AI, 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.
10 MCP Server for Crawl4AI tools catalogued and risk-classified — across an index of 43,000+ MCP servers.