Fetch any URL through residential proxy (2M+ IPs, 195 countries, anti-bot bypass). Returns JSON: ok, data.content, data.status_code, meta.latency_ms, meta.cache_hit.\n\nWHEN TO USE: Static/HTML pages, Amazon, LinkedIn, news sites, most commercial sites.\nUSE novada_proxy_render INSTEAD IF: Page r...
AI agents call novada_proxy_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.
novada_proxy_fetch retrieves webpage content via HTTP GET-style requests through residential proxies. This is fundamentally a Read operation: it queries remote servers and returns data without modifying or deleting anything. However, severity is elevated to 'high' due to the explicit anti-bot bypass and geo-spoofing capability (195 countries, 2M+ IPs).
From the tool's definition Tool description explicitly states 'Fetch any URL' and 'Returns JSON: ok, data.content, data.status_code' — purely retrieval of data. No modification, deletion, code execution, or financial transaction capability.
Attacks that exploit this kind of access
Fetch any URL through residential proxy (2M+ IPs, 195 countries, anti-bot bypass). Returns JSON: ok, data.content, data.status_code, meta.latency_ms, meta.cache_hit.\n\nWHEN TO USE: Static/HTML pages, Amazon, LinkedIn, news sites, most commercial sites.\nUSE novada_proxy_render INSTEAD IF: Page requires JavaScript to load (SPAs, React/Vue apps, dynamic feeds).\nUSE novada_proxy_extract INSTEAD IF: You need structured fields (title, price, rating) not raw content.\nON FAILURE: If error.code is BOT_DETECTION_SUSPECTED → retry with novada_proxy_render. If TLS_ERROR → retry with a different country parameter.\nCACHING: Same URL+format+country hits in-process cache (TTL 300s). meta.cache_hit=true = no credit used. session_id calls bypass cache. 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_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_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_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_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_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 →