adb_screen
Control screen state: wake, sleep, toggle, lock, or unlock. Lock and unlock verify actual keyguard state via dumpsys window. Unlock uses wm dismiss-keyguard (works for swipe keyguards); supply
This record as markdown: /tools/io-github-fullread-deepadb/adb-screen.md
What adb_screen does on Deepadb
AI agents invoke adb_screen to trigger actions in Deepadb. 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.
Why adb_screen is rated High
This tool executes device-level operations (waking, sleeping, locking, unlocking the screen) via ADB commands and system utilities like dumpsys and wm. These are external system operations that directly affect device state. Misuse could lock users out, bypass screen lock, or disrupt device access — making severity high.
From the tool's definition Control screen state: wake, sleep, toggle, lock, or unlock... Unlock uses wm dismiss-keyguard
Attacks that exploit this kind of access
The rule that runs adb_screen safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Deepadb, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For adb_screen, this is the rule to start with:
adb_screen 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Deepadb, apply this rule, and every adb_screen call is checked against it from then on.
Questions about adb_screen
Control screen state: wake, sleep, toggle, lock, or unlock. Lock and unlock verify actual keyguard state via dumpsys window. Unlock uses wm dismiss-keyguard (works for swipe keyguards); supply. It is categorised as a Execute tool in the Deepadb MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Deepadb MCP server in PolicyLayer and add a rule for adb_screen: 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 Deepadb. Nothing to install.
adb_screen 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_screen 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_screen. 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_screen is provided by the Deepadb MCP server (deepadb). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Deepadb, and thousands of servers like it.
Across the catalogue