Convert webpage to clean markdown format with content filtering options
AI agents call md 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.
This tool retrieves and transforms webpage content into a different format (markdown) for presentation purposes. It has no side effects on the target webpage or external systems—it reads publicly accessible or authorized web content and returns it in an alternative format. This is a classic Read category operation: data retrieval with content transformation but no state modification.
From the tool's definition Tool 'md' converts webpages to markdown format with content filtering. The description explicitly indicates data retrieval ('Convert webpage') with no modification or deletion of source content.
Documented attack patterns abuse exactly the kind of access md 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 md:
{
"version": "1",
"default": "deny",
"tools": {
"md": {}
}
}md 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.
Convert webpage to clean markdown format with content filtering options. 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 md: 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.
md 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 md 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 md. 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.
md 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.