scrape_markdown
AI agents call scrape_markdown to retrieve information from Crawl4AI MCP Wrapper without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and extracts markdown-formatted content from web pages. It performs no modifications, deletions, or code execution—purely data retrieval. Severity is medium rather than low because scraping can violate website terms of service, access rate limits, or extract sensitive data, creating reputational/legal risk if misused by an agent.
From the tool's definition Tool named 'scrape_markdown' on a web scraping/crawling server (Crawl4AI) that 'supports markdown extraction'. The description is empty, but the name and server context indicate content retrieval.
Attacks that exploit this kind of access
scrape_markdown. It is categorised as a Read tool in the Crawl4AI MCP Wrapper MCP Server, which means it retrieves data without modifying state.
Register the Crawl4AI MCP Wrapper MCP server in PolicyLayer and add a rule for scrape_markdown: 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 MCP Wrapper. Nothing to install.
scrape_markdown 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 scrape_markdown 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 scrape_markdown. 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.
scrape_markdown is provided by the Crawl4AI MCP Wrapper MCP server (joedank/mcpcrawl4ai). 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 →