Fetch multiple URLs concurrently through residential proxy. Returns structured JSON with per-URL results including ok/error status. Up to 20 URLs, up to 5 concurrent.\n\nWHEN TO USE: Scraping lists of URLs from search results, product catalogs, competitor pages.\nUSE novada_proxy_fetch INSTEAD FO...
AI agents call novada_proxy_batch_fetch to retrieve information from Novada Proxy without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
While the tool retrieves data (Read category), the severity is elevated to 'high' rather than 'low' because the server explicitly enables bypassing anti-bot systems and geo-targeting restrictions through residential IP rotation. An AI agent could use this to scrape protected content, violate terms of service, perform large-scale data exfiltration, or conduct reconnaissance on competitors or targets at scale.
From the tool's definition Tool description states it 'Fetch[es] multiple URLs concurrently' and returns 'structured JSON with per-URL results'.
Attacks that exploit this kind of access
Fetch multiple URLs concurrently through residential proxy. Returns structured JSON with per-URL results including ok/error status. Up to 20 URLs, up to 5 concurrent.\n\nWHEN TO USE: Scraping lists of URLs from search results, product catalogs, competitor pages.\nUSE novada_proxy_fetch INSTEAD FOR: Single URLs — lower overhead.\nON FAILURE: Individual URL failures are captured in results[].error — the batch itself succeeds even if some URLs fail. It is categorised as a Read tool in the Novada Proxy MCP Server, which means it retrieves data without modifying state.
Register the Novada Proxy MCP server in PolicyLayer and add a rule for novada_proxy_batch_fetch: 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 Novada Proxy. Nothing to install.
novada_proxy_batch_fetch 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 novada_proxy_batch_fetch 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 novada_proxy_batch_fetch. 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.
novada_proxy_batch_fetch is provided by the Novada Proxy MCP server (novadalabs/novada-proxy). 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 →