confirm_direction · Prompts MCP: Risk & Policy

WHAT IT DOES

What confirm_direction does on Prompts

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

WHY IT NEEDS A POLICY

Why confirm_direction needs a policy

This tool creates or modifies project direction documentation (direction.md) based on user confirmation during an AI dialogue. While the write is reversible (the file can be edited or deleted later), it does modify persistent project state. It does not execute arbitrary code, delete data irreversibly, or move money, so Write is the appropriate category.

From the tool's definition Tool description states it 'saves target, constraints, and acceptance criteria to direction.md' — this is a create/modify operation that writes data to a persistent file. The tool performs a reversible write action ('保存' = save/persist).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

confirm_direction Rate-limited

confirm_direction 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": {
    "confirm_direction": {
      "limits": [
        {
          "counter": "confirm_direction_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 Prompts, so you can run agents against it safely.

FAQ

Questions about confirm_direction

What does the confirm_direction tool do? +

【方向确认】AI 追问澄清后，用户确认方向时调用。保存目标、约束、验收标准到 direction.md。对话式追问由 AI 自然完成，此工具只负责持久化确认结果。. It is categorised as a Write tool in the Prompts MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on confirm_direction? +

Register the Prompts MCP server in PolicyLayer and add a rule for confirm_direction: 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 Prompts. Nothing to install.

What risk level is confirm_direction? +

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

Can I rate-limit confirm_direction? +

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

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

confirm_direction is provided by the Prompts MCP server (thana0623/pmcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.