onboard_tool · Prompts MCP: Risk & Policy

WHAT IT DOES

What onboard_tool does on Prompts

AI agents use onboard_tool 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 onboard_tool needs a policy

The tool generates and manages onboarding guides (prompts/documentation) for tools—a write operation that creates reversible content. It does not execute external code, delete data, or move money. Severity is low because generating guidance text has minimal blast radius; worst case is incorrect or misleading documentation, easily corrected.

From the tool's definition Tool name 'onboard_tool' and description indicate it 'generates...quick onboarding guidance' (是什么 → 用一次 → 验证效果) for tools. This creates or modifies guide/prompt content persistently within the system.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

onboard_tool Rate-limited

onboard_tool 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": {
    "onboard_tool": {
      "limits": [
        {
          "counter": "onboard_tool_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 onboard_tool

What does the onboard_tool tool do? +

【工具引导】为指定工具生成 3 步快速上手引导（是什么 → 用一次 → 验证效果）。. 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 onboard_tool? +

Register the Prompts MCP server in PolicyLayer and add a rule for onboard_tool: 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 onboard_tool? +

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

Can I rate-limit onboard_tool? +

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

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

onboard_tool 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.