AI agents call perplexity_query to retrieve information from Geoseo without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation: it submits a question to Perplexity and returns search results and citations. There is no data creation, modification, deletion, code execution, or financial transaction. The tool retrieves and presents information only, making it a straightforward Read category classification with low severity risk.
From the tool's definition Tool name 'perplexity_query' and description 'Ask Perplexity a question; return answer + cited URLs/domains' indicate a query operation that retrieves information from an external service (Perplexity LLM) without modifying any data or triggering side effects.
Attacks that exploit this kind of access
Ask Perplexity a question; return answer + cited URLs/domains. It is categorised as a Read tool in the Geoseo MCP Server, which means it retrieves data without modifying state.
Register the Geoseo MCP server in PolicyLayer and add a rule for perplexity_query: 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 Geoseo. Nothing to install.
perplexity_query 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 perplexity_query 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 perplexity_query. 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.
perplexity_query is provided by the Geoseo MCP server (rachit8484/geoseo-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 →