ami_execute · Ami MCP: Risk & Policy

WHAT IT DOES

What ami_execute does on Ami

AI agents invoke ami_execute to trigger actions in Ami. 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 ami_execute needs a policy

The tool name 'ami_execute' directly indicates execution of commands or code. While the description is absent (reducing confidence slightly), the name is unambiguous and the context—an MCP server for particle physics workflows—suggests this could trigger computationally intensive or external operations. Without execute semantics, this tool would be misnamed.

From the tool's definition Tool named 'ami_execute' with empty description; naming convention strongly suggests code/command execution capability. In context of ATLAS physics workflows, execution tools typically trigger analyses, simulations, or external processes.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

ami_execute Rate-limited

ami_execute 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": {
    "ami_execute": {
      "limits": [
        {
          "counter": "ami_execute_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 Ami, so you can run agents against it safely.

FAQ

Questions about ami_execute

What does the ami_execute tool do? +

ami_execute. It is categorised as a Execute tool in the Ami MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on ami_execute? +

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

What risk level is ami_execute? +

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

Can I rate-limit ami_execute? +

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

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

ami_execute is provided by the Ami MCP server (kratsg/ami-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.