async_research · Perplexity MCP Server MCP: Risk & Policy

WHAT IT DOES

What async_research does on Perplexity MCP Server

AI agents invoke async_research to trigger actions in Perplexity MCP Server. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why async_research needs a policy

This tool triggers external API operations (submitting and polling asynchronous research jobs) using Perplexity's sonar-deep-research model. It initiates and manages external processes, making it an Execute-category tool. The blast radius is medium — it consumes API resources and may return extensive web-scraped content, but does not directly modify or delete data.

From the tool's definition Submit and poll long-running asynchronous deep-research jobs (sonar-deep-research)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

async_research Rate-limited

async_research stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "async_research": {
      "limits": [
        {
          "counter": "async_research_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Perplexity MCP Server, so you can run agents against it safely.

FAQ

Questions about async_research

What does the async_research tool do? +

Submit and poll long-running asynchronous deep-research jobs (sonar-deep-research). Use this instead of. It is categorised as a Execute tool in the Perplexity MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on async_research? +

Register the Perplexity MCP Server MCP server in PolicyLayer and add a rule for async_research: 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.

What risk level is async_research? +

async_research is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit async_research? +

Yes. Add a rate_limit block to the async_research 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.

How do I block async_research completely? +

Set action: deny in the PolicyLayer policy for async_research. 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.

What MCP server provides async_research? +

async_research 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.