AI agents invoke nanokvm_send_text to trigger actions in NanoKVM 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.
Based on the server context, this tool likely sends keystrokes/text to a remotely controlled machine via keyboard emulation. Sending arbitrary text/keystrokes to a BIOS-level KVM can execute commands on the target machine, modify BIOS settings, or interact with any running software. This constitutes remote execution capability.
From the tool's definition Tool name 'nanokvm_send_text' on a server described as providing 'keyboard and mouse emulation' for 'BIOS-level management of servers and headless machines'
Documented attack patterns abuse exactly the kind of access nanokvm_send_text gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and NanoKVM MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for nanokvm_send_text:
{
"version": "1",
"default": "deny",
"tools": {
"nanokvm_send_text": {
"limits": [
{
"counter": "nanokvm_send_text_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}nanokvm_send_text 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.
nanokvm_send_text. It is categorised as a Execute tool in the NanoKVM MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the NanoKVM MCP Server MCP server in PolicyLayer and add a rule for nanokvm_send_text: 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 NanoKVM MCP Server. Nothing to install.
nanokvm_send_text 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 nanokvm_send_text 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 nanokvm_send_text. 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.
nanokvm_send_text is provided by the NanoKVM MCP Server MCP server (scgreenhalgh/nanokvm-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from NanoKVM 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.
19 NanoKVM MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.