Hold down a mouse button ('left', 'right', 'middle').
AI agents invoke mouse_down to trigger actions in Computer Control MCP. 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.
Holding a mouse button is an interactive computer control action that can trigger UI interactions, drag operations, or other context-dependent behaviors. Combined with other tools like drag_mouse, this can execute arbitrary UI operations. The effect depends entirely on what's on screen, making it Execute-level.
From the tool's definition Hold down a mouse button ('left', 'right', 'middle')
Documented attack patterns abuse exactly the kind of access mouse_down gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Computer Control MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for mouse_down:
{
"version": "1",
"default": "deny",
"tools": {
"mouse_down": {
"limits": [
{
"counter": "mouse_down_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}mouse_down 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.
Hold down a mouse button ('left', 'right', 'middle'). It is categorised as a Execute tool in the Computer Control MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Computer Control MCP server in PolicyLayer and add a rule for mouse_down: 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 Computer Control MCP. Nothing to install.
mouse_down 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 mouse_down 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 mouse_down. 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.
mouse_down is provided by the Computer Control MCP server (ab498/computer-control-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 15 Computer Control MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
15 Computer Control MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.