write_string_with_keys_held
AI agents invoke write_string_with_keys_held 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.
This tool appears to type/write a string into the remote desktop while holding modifier keys (e.g., Ctrl, Alt, Shift), which constitutes a keyboard control action on a remote desktop. This is an Execute-category action as it triggers external operations on the remote system. Severity is high because arbitrary keyboard input with modifier keys held can trigger dangerous shortcuts or commands on the remote desktop.
From the tool's definition Tool name 'write_string_with_keys_held' on a VNC server that provides 'mouse and keyboard control, and automation'
Documented attack patterns abuse exactly the kind of access write_string_with_keys_held 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 write_string_with_keys_held:
{
"version": "1",
"default": "deny",
"tools": {
"write_string_with_keys_held": {
"limits": [
{
"counter": "write_string_with_keys_held_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
} write_string_with_keys_held 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.
write_string_with_keys_held. 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 write_string_with_keys_held: 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.
write_string_with_keys_held 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 write_string_with_keys_held 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 write_string_with_keys_held. 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.
write_string_with_keys_held 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.