Automatically call this tool for interactive, conversational queries. This tool leverages Perplexitys web search capabilities to provide real-time information and maintains conversation history using an optional chat ID for contextual follow-ups.
AI agents call chat_perplexity 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.
The tool performs web searches and retrieves real-time information, which is a Read operation. The medium severity reflects that it uses browser automation, maintains conversation history, and could potentially expose sensitive queries or retrieve sensitive information, but it has no write/execute/destructive capabilities described.
From the tool's definition leverages Perplexity's web search capabilities to provide real-time information and maintains conversation history
Documented attack patterns abuse exactly the kind of access chat_perplexity gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Perplexity MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for chat_perplexity:
{
"version": "1",
"default": "deny",
"tools": {
"chat_perplexity": {}
}
}chat_perplexity 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.
Automatically call this tool for interactive, conversational queries. This tool leverages Perplexitys web search capabilities to provide real-time information and maintains conversation history using an optional chat ID for contextual follow-ups. 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 chat_perplexity: 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.
chat_perplexity 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 chat_perplexity 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 chat_perplexity. 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.
chat_perplexity is provided by the Perplexity MCP Server MCP server (wysh3/perplexity-mcp-zerver). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 Perplexity MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
6 Perplexity MCP Server tools catalogued and risk-classified — across an index of 42,500+ MCP servers.