Retrieve the result of a background Agent API run (one submitted with agent + background:true). Returns the current status and, once complete, the full output. Poll until status is
AI agents call agent_retrieve 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 retrieves pre-computed results from a background job submission. It queries the state of an existing operation and returns data without creating, modifying, or deleting anything. The action is purely informational (read-only). Polling for status completion is a standard retrieval pattern with no destructive or mutating side effects.
From the tool's definition Tool name 'agent_retrieve' and description 'Retrieve the result' indicate data retrieval. The description states it 'Returns the current status and...the full output' with no mention of modifications, deletions, or side effects beyond polling for completion…
Attacks that exploit this kind of access
Retrieve the result of a background Agent API run (one submitted with agent + background:true). Returns the current status and, once complete, the full output. Poll until status is. 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 agent_retrieve: 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.
agent_retrieve 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 agent_retrieve 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 agent_retrieve. 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.
agent_retrieve 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 →