AI agents invoke node_plugins_execute to trigger actions in Remnawave. 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 runs code (plugins) on remote VPN nodes, which can have significant side effects depending on plugin implementation. It is not merely querying or modifying configuration—it actively executes operations whose impact depends on plugin arguments and logic.
From the tool's definition Tool named 'node_plugins_execute' with description 'Execute a node plugin' directly indicates execution of arbitrary plugin code on VPN infrastructure nodes.
Documented attack patterns abuse exactly the kind of access node_plugins_execute gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Remnawave, and nothing reaches the server without passing your rules. This is the rule we recommend for node_plugins_execute:
{
"version": "1",
"default": "deny",
"tools": {
"node_plugins_execute": {
"limits": [
{
"counter": "node_plugins_execute_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}node_plugins_execute 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.
Execute a node plugin. It is categorised as a Execute tool in the Remnawave MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Remnawave MCP server in PolicyLayer and add a rule for node_plugins_execute: 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 Remnawave. Nothing to install.
node_plugins_execute 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 node_plugins_execute 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 node_plugins_execute. 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.
node_plugins_execute is provided by the Remnawave MCP server (trackline/mcp-remnawave). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 153 Remnawave tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
153 Remnawave tools catalogued and risk-classified — across an index of 42,500+ MCP servers.