Search Perplexity.ai with specific source selection. Lets you combine multiple sources (e.g. web + academic). Use this when source control matters; prefer
AI agents call search_advanced to retrieve information from Perplexity Web without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries data from Perplexity.ai without modifying, deleting, or executing arbitrary code. It has no side effects beyond returning search results. The source selection capability is a filtering/querying feature, not a write or destructive operation. Low severity because misuse results only in unwanted information retrieval, not data loss or financial impact.
From the tool's definition Tool performs 'web searches' and 'returns search results along with cited sources directly to the client.' The description emphasizes querying and retrieving information ('search'), with no mention of data modification, deletion, or execution of external…
Documented attack patterns abuse exactly the kind of access search_advanced gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Perplexity Web, and nothing reaches the server without passing your rules. This is the rule we recommend for search_advanced:
{
"version": "1",
"default": "deny",
"tools": {
"search_advanced": {}
}
}search_advanced 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.
Search Perplexity.ai with specific source selection. Lets you combine multiple sources (e.g. web + academic). Use this when source control matters; prefer. It is categorised as a Read tool in the Perplexity Web MCP Server, which means it retrieves data without modifying state.
Register the Perplexity Web MCP server in PolicyLayer and add a rule for search_advanced: 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 Perplexity Web. Nothing to install.
search_advanced 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 search_advanced 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 search_advanced. 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.
search_advanced is provided by the Perplexity Web MCP server (quequiere/perplexity-web-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Perplexity Web, 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.
3 Perplexity Web tools catalogued and risk-classified — across an index of 43,000+ MCP servers.