AI agents call scrape_url to retrieve information from ReActMCP Web Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Scraping a URL retrieves content from a web page without modifying it. This is fundamentally a read operation. Severity is medium rather than low because scraping could be abused to exfiltrate sensitive data, bypass access controls, or harvest information at scale, though the direct impact is confined to data retrieval.
From the tool's definition Tool name 'scrape_url' and sibling tools like 'crawl_website', 'extract_structured_data', and 'search_web' on a web search server indicate data retrieval operations.
Documented attack patterns abuse exactly the kind of access scrape_url gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and ReActMCP Web Search, and nothing reaches the server without passing your rules. This is the rule we recommend for scrape_url:
{
"version": "1",
"default": "deny",
"tools": {
"scrape_url": {}
}
}scrape_url 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.
scrape_url. It is categorised as a Read tool in the ReActMCP Web Search MCP Server, which means it retrieves data without modifying state.
Register the ReActMCP Web Search MCP server in PolicyLayer and add a rule for scrape_url: 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 ReActMCP Web Search. Nothing to install.
scrape_url 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_url 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_url. 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_url is provided by the ReActMCP Web Search MCP server (mshojaei77/reactmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from ReActMCP Web Search, 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.
7 ReActMCP Web Search tools catalogued and risk-classified — across an index of 43,000+ MCP servers.