safe_publish · Prompts MCP: Risk & Policy

WHAT IT DOES

What safe_publish does on Prompts

AI agents invoke safe_publish to trigger actions in Prompts. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.

WHY IT NEEDS A POLICY

Why safe_publish needs a policy

This tool executes a multi-step pipeline: it publishes to npm (external package registry), pushes to git (modifies remote repository), bumps version numbers, updates README, and runs npm link. These are chained external operations with broad blast radius — publishing to npm is irreversible in practical terms and affects all downstream consumers.

From the tool's definition 一键完成隐私审计 + 版本 bump + npm publish + git push + npm link + README 更新 (one-click: privacy audit + version bump + npm publish + git push + npm link + README update)

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

safe_publish Rate-limited

safe_publish stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "safe_publish": {
      "limits": [
        {
          "counter": "safe_publish_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-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 safe_publish

What does the safe_publish tool do? +

【安全发布】一键完成隐私审计 + 版本 bump + npm publish + git push + npm link + README 更新。. It is categorised as a Execute tool in the Prompts MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on safe_publish? +

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

safe_publish is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit safe_publish? +

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

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

safe_publish 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.