Start a stopped instance. instance_id: from list_instances
AI agents invoke start_instance to trigger actions in Morpheus 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.
Starting an instance is an operational action that executes a command to change the state of cloud infrastructure. While not destructive (the instance can be stopped again), it is not a simple data read or write—it triggers real-world infrastructure operations whose effects depend on the instance_id argument.
From the tool's definition Tool name 'start_instance' and description 'Start a stopped instance' indicates execution of an operation that triggers external infrastructure state changes.
Attacks that exploit this kind of access
Start a stopped instance. instance_id: from list_instances. It is categorised as a Execute tool in the Morpheus MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Morpheus MCP Server MCP server in PolicyLayer and add a rule for start_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 Morpheus MCP Server. Nothing to install.
start_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 start_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 start_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.
start_instance is provided by the Morpheus MCP Server MCP server (nixndme/morpheus-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →