enhance_prompt · Prompt Architect MCP: Risk & Policy

WHAT IT DOES

What enhance_prompt does on Prompt Architect

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

WHY IT NEEDS A POLICY

Why enhance_prompt needs a policy

This tool writes modified data (an enhanced prompt) back to the user, making it a Write operation rather than Read-only. Severity is medium because misuse could generate misleading or manipulated prompts that guide downstream AI behavior in unintended directions, but the damage is reversible and depends on how the enhanced prompt is used.

From the tool's definition Tool performs 'enhance' action which creates or modifies a prompt artifact. The description states it uses a 'prompt architect engine' to transform user input, resulting in a new enriched prompt.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

enhance_prompt Rate-limited

enhance_prompt 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": {
    "enhance_prompt": {
      "limits": [
        {
          "counter": "enhance_prompt_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 Prompt Architect, so you can run agents against it safely.

FAQ

Questions about enhance_prompt

What does the enhance_prompt tool do? +

Enhance a user prompt using prompt architect engine. It is categorised as a Write tool in the Prompt Architect MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on enhance_prompt? +

Register the Prompt Architect MCP server in PolicyLayer and add a rule for enhance_prompt: 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 Prompt Architect. Nothing to install.

What risk level is enhance_prompt? +

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

Can I rate-limit enhance_prompt? +

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

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

enhance_prompt is provided by the Prompt Architect MCP server (prompt-architect-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.