This record as markdown: /tools/io-github-portel-dev-ncp/stop-ec2-instance.md
What stop_ec2_instance does on Ncp
AI agents invoke stop_ec2_instance to trigger actions in Ncp. 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 stop_ec2_instance is rated High
This tool executes an action against AWS infrastructure (stopping an EC2 instance). While not destructive (the instance can be restarted) or financial, it is an Execute-class tool because it triggers external operations whose effects depend on which instance is targeted.
From the tool's definition Tool name is 'stop_ec2_instance' and description states it 'Stop[s] an EC2 instance', indicating it triggers an external AWS operation that changes infrastructure state.
Attacks that exploit this kind of access
The rule that runs stop_ec2_instance safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ncp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For stop_ec2_instance, this is the rule to start with:
stop_ec2_instance 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Ncp, apply this rule, and every stop_ec2_instance call is checked against it from then on.
Questions about stop_ec2_instance
Stop an EC2 instance. It is categorised as a Execute tool in the Ncp MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ncp MCP server in PolicyLayer and add a rule for stop_ec2_instance: 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 Ncp. Nothing to install.
stop_ec2_instance 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 stop_ec2_instance 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 stop_ec2_instance. 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.
stop_ec2_instance is provided by the Ncp MCP server (@portel/ncp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ncp, and thousands of servers like it.
This server
Across the catalogue