Connect to a VNC server
AI agents invoke vnc_connect to trigger actions in VNC 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.
Establishing a VNC connection is the gateway action that enables full computer control (mouse, keyboard, screen capture, command execution). While 'connect' itself is a setup action, it triggers an external session with significant blast radius: once connected, an AI agent can execute arbitrary actions on the remote system.
From the tool's definition Connect to a VNC server — initiates an active remote desktop connection, enabling subsequent control of a remote computer
Attacks that exploit this kind of access
Connect to a VNC server. It is categorised as a Execute tool in the VNC MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the VNC MCP Server MCP server in PolicyLayer and add a rule for vnc_connect: 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 MCP Server. Nothing to install.
vnc_connect 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 vnc_connect 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 vnc_connect. 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.
vnc_connect is provided by the VNC MCP Server MCP server (volkan-m/vnc-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →