AI agents invoke strike_keys to trigger actions in Vnc. 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.
The server description explicitly mentions keyboard control and automation for VNC desktops. 'strike_keys' strongly implies simulating keystrokes on the remote desktop, which is an Execute-class action — it triggers external operations on a live desktop. Sibling tools confirm this context. Severity is high because arbitrary keystrokes on a remote desktop can run commands, delete files, or cause significant harm.
From the tool's definition Tool name 'strike_keys' on a VNC automation server with sibling tools for mouse/keyboard control; description is empty.
Documented attack patterns abuse exactly the kind of access strike_keys gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Vnc, and nothing reaches the server without passing your rules. This is the rule we recommend for strike_keys:
{
"version": "1",
"default": "deny",
"tools": {
"strike_keys": {
"limits": [
{
"counter": "strike_keys_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}strike_keys 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.
strike_keys. It is categorised as a Execute tool in the Vnc MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Vnc MCP server in PolicyLayer and add a rule for strike_keys: 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 Vnc. Nothing to install.
strike_keys 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 strike_keys 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 strike_keys. 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.
strike_keys is provided by the Vnc MCP server (regulad/vnc-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Vnc, 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.
20 Vnc tools catalogued and risk-classified — across an index of 43,000+ MCP servers.