AI agents invoke start_application to trigger actions in AWS Support 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.
Without a description, we infer behavior from the name. 'start_application' implies executing or launching an application rather than merely reading or writing data. This is an Execute-class action because it triggers an external operation with effects that could be significant (resource consumption, state changes, side effects depending on which application starts).
From the tool's definition Tool name is 'start_application' with no description provided. The name suggests initiating or launching an application, which constitutes triggering an external operation whose effects depend on what application is started and in what context.
Documented attack patterns abuse exactly the kind of access start_application gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and AWS Support MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for start_application:
{
"version": "1",
"default": "deny",
"tools": {
"start_application": {
"limits": [
{
"counter": "start_application_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}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.
Free to start. No card required.
start_application. It is categorised as a Execute tool in the AWS Support MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the AWS Support MCP Server MCP server in PolicyLayer and add a rule for 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 AWS Support MCP Server. Nothing to install.
start_application is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the 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.
Set action: deny in the PolicyLayer policy for 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.
start_application is provided by the AWS Support MCP Server MCP server (awslabs.aws-support-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from AWS Support MCP Server, 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.
805 AWS Support MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.