Get the planning questions to ask the user. Call this FIRST when a user wants to build something, then ask each question conversationally. After collecting all answers, call pmpt_plan to generate the project.
AI agents call pmpt_plan_questions to retrieve information from Pmpt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool fetches/retrieves planning questions to present to the user. It is a read-only operation that returns structured prompts/questions. The instruction to call it 'FIRST' and then later call pmpt_plan confirms it is purely a data-retrieval step with no write, execute, or destructive behavior.
From the tool's definition 'Get the planning questions to ask the user' — retrieves a list of questions; no data modification or side effects described
Documented attack patterns abuse exactly the kind of access pmpt_plan_questions gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Pmpt, and nothing reaches the server without passing your rules. This is the rule we recommend for pmpt_plan_questions:
{
"version": "1",
"default": "deny",
"tools": {
"pmpt_plan_questions": {}
}
}pmpt_plan_questions is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get the planning questions to ask the user. Call this FIRST when a user wants to build something, then ask each question conversationally. After collecting all answers, call pmpt_plan to generate the project. It is categorised as a Read tool in the Pmpt MCP Server, which means it retrieves data without modifying state.
Register the Pmpt MCP server in PolicyLayer and add a rule for pmpt_plan_questions: 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 Pmpt. Nothing to install.
pmpt_plan_questions 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 pmpt_plan_questions 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 pmpt_plan_questions. 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.
pmpt_plan_questions is provided by the Pmpt MCP server (pmptwiki/pmpt-cli). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Pmpt, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
14 Pmpt tools catalogued and risk-classified — across an index of 43,000+ MCP servers.