This record as markdown: /tools/cbrown35-20i-mcp/start-vps.md
What start_vps does on 20i MCP Server
AI agents invoke start_vps to trigger actions in 20i 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.
Why start_vps is rated High
Starting a VPS is an Execute action—it triggers an external operation (VPS boot) whose effects depend on which VPS is targeted. While not immediately destructive, it commits infrastructure resources and can affect hosted services. This poses significant risk if an AI agent targets the wrong VPS or acts without proper authorization, justifying high severity.
From the tool's definition Tool name 'start_vps' and description 'Start a stopped VPS' indicate execution of infrastructure operations that trigger external state changes (VPS startup).
Attacks that exploit this kind of access
The rule that runs start_vps safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 20i MCP Server, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For start_vps, this is the rule to start with:
start_vps 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 20i MCP Server, apply this rule, and every start_vps call is checked against it from then on.
Questions about start_vps
Start a stopped VPS. It is categorised as a Execute tool in the 20i MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the 20i MCP Server MCP server in PolicyLayer and add a rule for start_vps: 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 20i MCP Server. Nothing to install.
start_vps 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_vps 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_vps. 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_vps is provided by the 20i MCP Server MCP server (cbrown35/20i-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 20i MCP Server, and thousands of servers like it.
Across the catalogue