step_complete · Shotter MCP: Risk & Policy

WHAT IT DOES

What step_complete does on Shotter

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

WHY IT NEEDS A POLICY

Why step_complete needs a policy

An AI agent can call step_complete faster than any human can review — one bad instruction and it creates or modifies resources in Shotter by the hundred, each call as confident as the last.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

step_complete Rate-limited

step_complete 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": {
    "step_complete": {
      "limits": [
        {
          "counter": "step_complete_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 Shotter, so you can run agents against it safely.

FAQ

Questions about step_complete

What does the step_complete tool do? +

Signal that the current navigation step goal has been achieved. Call this when you have successfully completed the goal, or when you determine the goal cannot be achieved. It is categorised as a Write tool in the Shotter MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on step_complete? +

Register the Shotter MCP server in PolicyLayer and add a rule for step_complete: 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 Shotter. Nothing to install.

What risk level is step_complete? +

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

Can I rate-limit step_complete? +

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

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

step_complete is provided by the Shotter MCP server (nathanstitt/shotter). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.