plan_from_text · PDDL MCP Server MCP: Risk & Policy

WHAT IT DOES

What plan_from_text does on PDDL MCP Server

AI agents invoke plan_from_text to trigger actions in PDDL 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 plan_from_text needs a policy

This tool runs the Fast Downward planner and executes planning operations based on arbitrary natural-language input. Since it involves executing an external planner with dynamically generated PDDL, the blast radius is high — a misused or adversarially crafted input could trigger unintended planning operations, resource exhaustion, or multi-robot coordination commands.

From the tool's definition 'Plan from a natural-language task description' — converts natural language to PDDL and executes planning using the Fast Downward planner, triggering external computation and batch task execution

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

plan_from_text Rate-limited

plan_from_text 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": {
    "plan_from_text": {
      "limits": [
        {
          "counter": "plan_from_text_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 PDDL MCP Server, so you can run agents against it safely.

FAQ

Questions about plan_from_text

What does the plan_from_text tool do? +

Plan from a natural-language task description. It is categorised as a Execute tool in the PDDL 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 plan_from_text? +

Register the PDDL MCP Server MCP server in PolicyLayer and add a rule for plan_from_text: 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 PDDL MCP Server. Nothing to install.

What risk level is plan_from_text? +

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

Can I rate-limit plan_from_text? +

Yes. Add a rate_limit block to the plan_from_text 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_from_text completely? +

Set action: deny in the PolicyLayer policy for plan_from_text. 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_from_text? +

plan_from_text is provided by the PDDL MCP Server MCP server (nbnbtm/pddl-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.