Medium Risk

gateway.set_startup_policy

Preview or explicitly apply an autoStart add/remove/set operation

How to control gateway.set_startup_policy ↓

What gateway.set_startup_policy does on PMCP

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

Medium Risk

Why gateway.set_startup_policy needs a policy

This tool writes/modifies the gateway's startup policy by adding, removing, or setting autoStart configurations. This is a Write operation as it changes configuration state. Severity is high because misconfiguring startup policies could affect which downstream servers are automatically provisioned, potentially disrupting service availability or causing unintended servers to start.

From the tool's definition 'explicitly apply an autoStart add/remove/set operation' — modifies startup policy configuration for server auto-start behavior

Documented attack patterns abuse exactly the kind of access gateway.set_startup_policy gives an agent:

How to control gateway.set_startup_policy

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "gateway.set_startup_policy": {
      "limits": [
        {
          "counter": "gateway.set_startup_policy_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

gateway.set_startup_policy 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.

  1. Create a free account and register PMCP — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
LIMIT THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about gateway.set_startup_policy

What does the gateway.set_startup_policy tool do? +

Preview or explicitly apply an autoStart add/remove/set operation. It is categorised as a Write tool in the PMCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on gateway.set_startup_policy? +

Register the P MCP server in PolicyLayer and add a rule for gateway.set_startup_policy: 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 PMCP. Nothing to install.

What risk level is gateway.set_startup_policy? +

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

Can I rate-limit gateway.set_startup_policy? +

Yes. Add a rate_limit block to the gateway.set_startup_policy 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 gateway.set_startup_policy completely? +

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

gateway.set_startup_policy is provided by the P MCP server (viperjuice/pmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every PMCP tool call.

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

Free to start. No card required.

26 PMCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.