Crawl a URL and return HTML content. Pass store=true to push the result to Crawlbase Cloud Storage instead of returning the body — the response will then contain only the RID and metadata, which can later be retrieved via storage_get.
AI agents call crawl to retrieve information from Crawlbase MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The crawl tool's primary function is fetching and retrieving web content ('return HTML content'), a classic Read operation. While it can store results to Crawlbase Cloud Storage internally, it does not write to or modify the external resource being crawled.
From the tool's definition Tool description states 'Crawl a URL and return HTML content' and 'retrieve via storage_get', which are retrieval operations. Optional store=true pushes to storage but does not modify external web content.
Documented attack patterns abuse exactly the kind of access crawl gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crawlbase MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for crawl:
{
"version": "1",
"default": "deny",
"tools": {
"crawl": {}
}
}crawl 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.
Crawl a URL and return HTML content. Pass store=true to push the result to Crawlbase Cloud Storage instead of returning the body — the response will then contain only the RID and metadata, which can later be retrieved via storage_get. It is categorised as a Read tool in the Crawlbase MCP MCP Server, which means it retrieves data without modifying state.
Register the Crawlbase MCP server in PolicyLayer and add a rule for 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 Crawlbase MCP. Nothing to install.
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 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 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.
crawl is provided by the Crawlbase MCP server (crawlbase/crawlbase-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crawlbase MCP, 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.
9 Crawlbase MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.