generate_plan · PDDL MCP Server MCP: Risk & Policy

WHAT IT DOES

What generate_plan does on PDDL MCP Server

AI agents invoke generate_plan 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 generate_plan needs a policy

This tool runs an external planning engine (Fast Downward) to generate plans from PDDL inputs. It executes an external process whose effects depend on the provided task arguments. No data is permanently deleted, but it triggers computation and potentially external operations, placing it in the Execute category.

From the tool's definition 'Plan from a task dictionary or existing domain/problem PDDL paths' — triggers the Fast Downward planner to execute a planning operation

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_plan Rate-limited

generate_plan 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": {
    "generate_plan": {
      "limits": [
        {
          "counter": "generate_plan_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 generate_plan

What does the generate_plan tool do? +

Plan from a task dictionary or existing domain/problem PDDL paths. 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 generate_plan? +

Register the PDDL MCP Server MCP server in PolicyLayer and add a rule for generate_plan: 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 generate_plan? +

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

Can I rate-limit generate_plan? +

Yes. Add a rate_limit block to the generate_plan 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 generate_plan completely? +

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

generate_plan 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.