runtime_start_application · Anypoint MCP Server MCP

WHAT IT DOES

What runtime_start_application does on Anypoint MCP Server

AI agents invoke runtime_start_application to trigger actions in Anypoint MCP Server. 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 runtime_start_application needs a policy

Starting an application in a runtime manager is an executable action that initiates external processes and services. While not destructive or financial, it modifies system state irreversibly in the immediate sense (an application is now running) and can have broad side effects depending on the application's purpose and dependencies. This warrants 'Execute' classification.

From the tool's definition Tool name contains 'start' and description states 'Start a stopped Runtime Manager application' — this triggers an external operation (application startup) whose effects depend on which deployment is targeted via the deploymentId argument.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

runtime_start_application Rate-limited

runtime_start_application 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": {
    "runtime_start_application": {
      "limits": [
        {
          "counter": "runtime_start_application_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 Anypoint MCP Server, so you can run agents against it safely.

FAQ

Questions about runtime_start_application

What does the runtime_start_application tool do? +

Start a stopped Runtime Manager application. Call runtime_list_deployments first to obtain the deploymentId. It is categorised as a Execute tool in the Anypoint MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on runtime_start_application? +

Register the Anypoint MCP Server MCP server in PolicyLayer and add a rule for runtime_start_application: 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 Anypoint MCP Server. Nothing to install.

What risk level is runtime_start_application? +

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

Can I rate-limit runtime_start_application? +

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

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

runtime_start_application is provided by the Anypoint MCP Server MCP server (sravannerella/mulesoft-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.