Direct web search returning ranked results without LLM synthesis. Faster and cheaper than
AI agents call raw_search to retrieve information from Perplexity MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a direct web search and returns ranked results without modification or synthesis. It is a pure information retrieval operation with no capability to create, modify, delete, execute code, or commit financial transactions. The primary risk is exposure of search queries themselves, which is minimal and typical of read-only tools.
From the tool's definition Tool name 'raw_search' combined with description stating 'Direct web search returning ranked results' indicates retrieval and querying of data.
Attacks that exploit this kind of access
Direct web search returning ranked results without LLM synthesis. Faster and cheaper than. It is categorised as a Read tool in the Perplexity MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Perplexity MCP Server MCP server in PolicyLayer and add a rule for raw_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 Perplexity MCP Server. Nothing to install.
raw_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 raw_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 raw_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.
raw_search is provided by the Perplexity MCP Server MCP server (rossh121/perplexity-mcp). 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 →