prompt_retrospective · MCP SAPUI5 Server MCP: Risk & Policy

WHAT IT DOES

What prompt_retrospective does on MCP SAPUI5 Server

AI agents use prompt_retrospective to create or update resources in MCP SAPUI5 Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP SAPUI5 Server environment.

WHY IT NEEDS A POLICY

Why prompt_retrospective needs a policy

This tool primarily performs analysis (read-like introspection) but has the capability to create or modify retrospective logs in a project directory. The write operation is reversible—logs can be deleted or modified—making it Write rather than Destructive. The blast radius is low since it only writes diagnostic/analysis metadata files, not core application logic or data.

From the tool's definition The tool description states it can 'optionally persist retrospective logs under .codex/mcp', indicating write operations to the filesystem. The verb 'persist' and the specification of a directory path (.codex/mcp) confirm data creation/modification capability.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

prompt_retrospective Rate-limited

prompt_retrospective 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": {
    "prompt_retrospective": {
      "limits": [
        {
          "counter": "prompt_retrospective_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 MCP SAPUI5 Server, so you can run agents against it safely.

FAQ

Questions about prompt_retrospective

What does the prompt_retrospective tool do? +

Analyze prompt execution outcome, suggest quality improvements, and optionally persist retrospective logs under .codex/mcp. It is categorised as a Write tool in the MCP SAPUI5 Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on prompt_retrospective? +

Register the MCP SAPUI5 Server MCP server in PolicyLayer and add a rule for prompt_retrospective: 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 MCP SAPUI5 Server. Nothing to install.

What risk level is prompt_retrospective? +

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

Can I rate-limit prompt_retrospective? +

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

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

prompt_retrospective is provided by the MCP SAPUI5 Server MCP server (santiagosanmartinn/mcpui5server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.