Search Google and return structured results (title, url, snippet) as JSON. No HTML parsing needed — results are pre-structured.\n\nWHEN TO USE: Finding pages by topic, factual queries, discovering URLs to then fetch.\nUSE novada_proxy_fetch INSTEAD FOR: Reading a specific URL you already have.\nO...
AI agents call novada_proxy_search 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 this tool performs a basic read operation (searching and returning results), the severity is elevated to medium rather than low because it operates through the Novada Proxy infrastructure which 'enables AI agents to route HTTP requests through millions of real residential IPs, bypassing anti-bot systems and geo-targeting.' This capability to circumvent security controls and anti-bot measures through IP…
From the tool's definition Tool description states it 'Search Google and return structured results' and is used for 'Finding pages by topic, factual queries, discovering URLs'. The primary action is retrieval and querying, which is characteristic of a Read operation.
Attacks that exploit this kind of access
Search Google and return structured results (title, url, snippet) as JSON. No HTML parsing needed — results are pre-structured.\n\nWHEN TO USE: Finding pages by topic, factual queries, discovering URLs to then fetch.\nUSE novada_proxy_fetch INSTEAD FOR: Reading a specific URL you already have.\nON FAILURE: If error.code is PROVIDER_NOT_CONFIGURED → set NOVADA_API_KEY. 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_search: 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_search 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_search 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_search. 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_search 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 →