Manage LocalStack lifecycle: start, stop, restart, or check status
AI agents invoke localstack-management to trigger actions in Localstack. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
action | string | Yes | The LocalStack management action to perform |
envVars | object | — | Additional environment variables as key-value pairs (only for start action) |
service | string | — | The LocalStack stack/service to manage. Use 'aws' for the default AWS emulator, or 'snowflake' for the Snowflake emulator. |
Parameters from the server's own tool schema.
While the 'check status' operation is Read-like, the primary capabilities (start, stop, restart) are Execute operations that trigger container lifecycle changes. These are external operations that run as a consequence of the tool call. The severity is high because unintended container restarts or shutdowns could disrupt infrastructure and services, though not irreversible (Destructive) or financial in nature.
From the tool's definition Tool performs lifecycle management operations: "start, stop, restart, or check status" on LocalStack containers.
Attacks that exploit this kind of access
Manage LocalStack lifecycle: start, stop, restart, or check status. It is categorised as a Execute tool in the Localstack MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
localstack-management accepts 3 parameters: action, envVars, service. Required: action. The full parameter table on this page comes from the server's own tool schema.
Register the Localstack MCP server in PolicyLayer and add a rule for localstack-management: 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 Localstack. Nothing to install.
localstack-management 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 localstack-management 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 localstack-management. 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.
localstack-management is provided by the Localstack MCP server (@localstack/localstack-mcp-server). 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 →