Click at specific coordinates on the device screen
AI agents invoke adb_click to trigger actions in ADB 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.
This tool triggers a UI interaction (tap/click) on an Android device screen. It executes an action on an external device whose effects are entirely dependent on what is currently displayed and the coordinates provided. An AI agent could misuse this to confirm purchases, grant permissions, interact with sensitive UI elements, or perform unintended actions on the device.
From the tool's definition Click at specific coordinates on the device screen
Attacks that exploit this kind of access
Click at specific coordinates on the device screen. It is categorised as a Execute tool in the ADB MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the ADB MCP Server MCP server in PolicyLayer and add a rule for adb_click: 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 ADB MCP Server. Nothing to install.
adb_click 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 adb_click 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 adb_click. 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.
adb_click is provided by the ADB MCP Server MCP server (richard0913/adb-mcp). 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 →