Restart an instance
AI agents invoke restart_instance to trigger actions in Mcp Ap2. 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.
This tool executes an external operation (restart) that has real-world effects on system availability and state. It is not a simple read operation, nor does it permanently destroy data (making it less severe than Destructive), but it does trigger an action whose consequences depend on arguments provided. The high severity reflects that restarting critical payment infrastructure could disrupt financial transactions.
From the tool's definition Tool name is 'restart_instance' with description 'Restart an instance'. In the context of an AP2 (Agent-to-Agent Payment Protocol) server, 'instance' likely refers to a service or system instance.
Documented attack patterns abuse exactly the kind of access restart_instance gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Ap2, and nothing reaches the server without passing your rules. This is the rule we recommend for restart_instance:
{
"version": "1",
"default": "deny",
"tools": {
"restart_instance": {
"limits": [
{
"counter": "restart_instance_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} restart_instance 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.
Free to start. No card required.
Restart an instance. It is categorised as a Execute tool in the Mcp Ap2 MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Ap2 MCP server in PolicyLayer and add a rule for restart_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 Mcp Ap2. Nothing to install.
restart_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 restart_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 restart_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.
restart_instance is provided by the Mcp Ap2 MCP server (@codespar/mcp-ap2). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Mcp Ap2, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
1300 Mcp Ap2 tools catalogued and risk-classified — across an index of 43,000+ MCP servers.