plan_query · Literature Agent MCP: Risk & Policy

WHAT IT DOES

What plan_query does on Literature Agent

AI agents use plan_query to create or update resources in Literature Agent — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Literature Agent environment.

WHY IT NEEDS A POLICY

Why plan_query needs a policy

This tool creates/generates a planning document (JSON structure) that guides downstream literature retrieval tasks, making it a Write operation. It does not execute queries itself, retrieve live data, or cause irreversible changes. The severity is low because the output is a reversible plan/configuration that does not directly access external systems or modify persistent state.

From the tool's definition Tool generates a 'query plan JSON' which is a structured data output that represents instructions or configuration for a subsequent operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

plan_query Rate-limited

plan_query stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "plan_query": {
      "limits": [
        {
          "counter": "plan_query_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

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

FAQ

Questions about plan_query

What does the plan_query tool do? +

Generate a query plan JSON for a biomedical/pathology literature task. It is categorised as a Write tool in the Literature Agent MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on plan_query? +

Register the Literature Agent MCP server in PolicyLayer and add a rule for plan_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 Literature Agent. Nothing to install.

What risk level is plan_query? +

plan_query is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit plan_query? +

Yes. Add a rate_limit block to the plan_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.

How do I block plan_query completely? +

Set action: deny in the PolicyLayer policy for plan_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.

What MCP server provides plan_query? +

plan_query is provided by the Literature Agent MCP server (zouxy111/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.