AI agents invoke infra_restart_tool to trigger actions in Infra. 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.
Restarting a service is an Execute action: it runs an external operation (systemctl/docker restart) with side effects that depend on arguments (which service). Although gated by a confirmation requirement and service allowlist, these are guardrails rather than category-shifters.
From the tool's definition Tool name 'infra_restart_tool' and description 'Restart a compose service' explicitly perform a service restart operation on a remote VPS via Docker Compose.
Attacks that exploit this kind of access
Restart a compose service. Requires confirm=true AND service in INFRA_ALLOWED_SERVICES. It is categorised as a Execute tool in the Infra MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Infra MCP server in PolicyLayer and add a rule for infra_restart_tool: 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 Infra. Nothing to install.
infra_restart_tool 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 infra_restart_tool 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 infra_restart_tool. 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.
infra_restart_tool is provided by the Infra MCP server (odanree/infra-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 →