Research a topic by searching the web, fetching top results, and returning structured findings with sources. The findings_summary concatenates source previews — your agent should analyze findings[] for deeper synthesis.\n\nWHEN TO USE: Research questions, topic investigation, competitive analysis...
AI agents call novada_proxy_research 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.
This tool searches the web and retrieves content from URLs, returning structured findings — purely a read/query operation with no data modification. Severity is medium because it routes through residential IPs to bypass anti-bot systems, which could enable scraping at scale or circumvent access controls, but the tool itself only retrieves data.
From the tool's definition Research a topic by searching the web, fetching top results, and returning structured findings with sources
Attacks that exploit this kind of access
Research a topic by searching the web, fetching top results, and returning structured findings with sources. The findings_summary concatenates source previews — your agent should analyze findings[] for deeper synthesis.\n\nWHEN TO USE: Research questions, topic investigation, competitive analysis, fact-finding.\nUSE novada_proxy_search INSTEAD IF: You just need search results (titles + URLs), not full content.\nUSE novada_proxy_fetch INSTEAD IF: You already know which URL to read.\nCHAIN WITH: The findings_summary is a starting point — use novada_proxy_fetch on specific urls[] for deeper reading.\nON FAILURE: If PROVIDER_NOT_CONFIGURED → set NOVADA_API_KEY (required for search step). 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_research: 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_research 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_research 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_research. 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_research 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 →