AI agents call scrape to retrieve information from WebSearch without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Web scraping is fundamentally a data retrieval operation—it fetches and extracts information from web content. While scraping can be used unethically (e.g., violating terms of service, rate-limiting servers, or accessing protected content), the tool itself performs no reversible modifications, deletions, or financial transactions. It falls under Read category.
From the tool's definition Tool name is 'scrape' on a server described as providing 'web scraping capabilities.' The empty description limits certainty, but scraping typically retrieves and extracts data from web pages without modifying them.
Attacks that exploit this kind of access
scrape. It is categorised as a Read tool in the WebSearch MCP Server, which means it retrieves data without modifying state.
Register the WebSearch MCP server in PolicyLayer and add a rule for scrape: 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 WebSearch. Nothing to install.
scrape 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 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. 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 is provided by the WebSearch MCP server (josemartinrodriguezmortaloni/websearch-tools). 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 →