Get cleaned and preprocessed HTML content for further processing
AI agents call html to retrieve information from Crawl4ai without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves and returns HTML content from web pages after cleaning and preprocessing. There are no side effects, no data modification, no code execution, and no destructive operations. This is purely a data retrieval function with low blast radius if misused by an AI agent—worst case would be excessive requests or accessing unintended web content.
From the tool's definition Tool name 'html' with description 'Get cleaned and preprocessed HTML content for further processing' indicates retrieval of web page HTML without modification. This is a read-only operation similar to the 'md' and 'screenshot' tools on the same server.
Documented attack patterns abuse exactly the kind of access html gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crawl4ai, and nothing reaches the server without passing your rules. This is the rule we recommend for html:
{
"version": "1",
"default": "deny",
"tools": {
"html": {}
}
}html 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.
Get cleaned and preprocessed HTML content for further processing. It is categorised as a Read tool in the Crawl4ai MCP Server, which means it retrieves data without modifying state.
Register the Crawl4ai MCP server in PolicyLayer and add a rule for html: 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 Crawl4ai. Nothing to install.
html 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 html 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 html. 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.
html is provided by the Crawl4ai MCP server (stgmt/crawl4ai-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from 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.
6 Crawl4ai tools catalogued and risk-classified — across an index of 43,000+ MCP servers.