AI agents invoke start_all_nodes to trigger actions in EVE-NG 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.
Starting nodes in a network emulation lab is an execution action that initiates external processes and changes the operational state of network infrastructure. While not destructive (nodes can be stopped), it is an Execute-category tool because it runs/triggers operations whose side effects depend on arguments and cannot be trivially undone without further action.
From the tool's definition Tool name is 'start_all_nodes' and description states it 'Start all nodes in a lab.' This triggers external operations (network emulation node startup) whose effects depend on the lab context provided as an argument.
Documented attack patterns abuse exactly the kind of access start_all_nodes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and EVE-NG MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for start_all_nodes:
{
"version": "1",
"default": "deny",
"tools": {
"start_all_nodes": {
"limits": [
{
"counter": "start_all_nodes_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} start_all_nodes 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.
Start all nodes in a lab. It is categorised as a Execute tool in the EVE-NG MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the EVE-NG MCP Server MCP server in PolicyLayer and add a rule for start_all_nodes: 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 EVE-NG MCP Server. Nothing to install.
start_all_nodes 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_all_nodes 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_all_nodes. 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_all_nodes is provided by the EVE-NG MCP Server MCP server (moimran/eveng-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from EVE-NG MCP Server, 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.
26 EVE-NG MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.