publish_agent

THE RISK

High Risk

Why publish_agent needs a policy

Publishing an agent version is an external operation that changes which version is live/active in a system. This is not a simple write (it has operational consequences — activating code or logic that runs in production), nor clearly destructive (previous versions may still exist). It most closely maps to Execute due to triggering an external deployment operation.

From the tool's definition 'Publish a specific agent version, making it the active/live version' — triggers an external deployment/activation operation

Documented attack patterns abuse exactly the kind of access publish_agent gives an agent:

POLICY

How to control publish_agent

PolicyLayer is an MCP gateway — it sits between your AI agents and Apple Shortcuts, and nothing reaches the server without passing your rules. This is the rule we recommend for publish_agent:

policy.json

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

publish_agent 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.

Create a free account and register Apple Shortcuts — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

Related tools and policies

More Apple Shortcuts tools

Destructive cancel_runway_task Cancel a pending/running task or delete a completed task. Saves credits if cancelled befor Destructive delete_custom_voice Delete a custom voice by ID. This is permanent and cannot be undone. Destructive delete_email Delete or move an email to trash. Destructive delete_event Delete a calendar event. Destructive delete_file Delete a file or folder from OneDrive. Destructive delete_library_item Delete a file or folder from a SharePoint document library. Destructive delete_list_item Delete an item from a SharePoint list. Destructive opus_cancel_scheduled_post Cancel a scheduled social post BEFORE its publishAt time.

All 423 Apple Shortcuts tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Apple Shortcuts → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about publish_agent

What does the publish_agent tool do? +

Publish a specific agent version, making it the active/live version. WHEN TO USE: - After updating an agent. It is categorised as a Execute tool in the Apple Shortcuts MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on publish_agent? +

Register the Apple Shortcuts MCP server in PolicyLayer and add a rule for publish_agent: 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 Apple Shortcuts. Nothing to install.

What risk level is publish_agent? +

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

Can I rate-limit publish_agent? +

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

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

publish_agent is provided by the Apple Shortcuts MCP server (@mindstone/mcp-server-apple-shortcuts). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Apple Shortcuts tool call.

Start from Apple Shortcuts, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →