AI agents invoke click_at_position to trigger actions in GachaMCP. 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 performs UI automation by clicking at specific coordinates within a game window. Clicks can trigger purchases, confirmations, in-game transactions (e.g., gacha pulls which may involve real or virtual currency), or other irreversible actions depending on where the click lands.
From the tool's definition 'click_at_position' - clicks at specific coordinates on the game window; part of a click automation system described in server description as 'click automation'
Attacks that exploit this kind of access
Click tại tọa độ cụ thể trên cửa sổ game. It is categorised as a Execute tool in the GachaMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Gacha MCP server in PolicyLayer and add a rule for click_at_position: 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 GachaMCP. Nothing to install.
click_at_position 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 click_at_position 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 click_at_position. 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.
click_at_position is provided by the Gacha MCP server (nguyenhuynhphuvinh/gachamcp). 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 →