Perform an action on a DigitalOcean droplet
AI agents invoke do_droplet_action to trigger actions in Cargoshipper. 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.
Performing actions on a DigitalOcean droplet covers a wide range of operations such as rebooting, shutting down, rebuilding, or resizing a VM. These are external operations with real infrastructure impact. While some actions may be reversible (reboot), others (rebuild, restore) can cause data loss or significant disruption.
From the tool's definition "Perform an action on a DigitalOcean droplet" — triggering actions on cloud compute instances (reboot, power off, rebuild, resize, etc.)
Attacks that exploit this kind of access
Perform an action on a DigitalOcean droplet. It is categorised as a Execute tool in the Cargoshipper MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cargoshipper MCP server in PolicyLayer and add a rule for do_droplet_action: 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 Cargoshipper. Nothing to install.
do_droplet_action 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 do_droplet_action 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 do_droplet_action. 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.
do_droplet_action is provided by the Cargoshipper MCP server (scarr7981/cargoshipper-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 →