adb_input_long_press
Long press at a point on screen. Triggers context menus, selection mode, drag handles, and other long-press behaviors. Implemented as a zero-distance swipe with configurable hold duration.
This record as markdown: /tools/io-github-fullread-deepadb/adb-input-long-press.md
What adb_input_long_press does on Deepadb
AI agents invoke adb_input_long_press 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_input_long_press is rated High
This tool executes a UI interaction (long press gesture) on an Android device via ADB, triggering device-side behaviors such as context menus and selection mode. It runs an external operation whose effects depend on arguments (coordinates, duration, and what app/element is under the press), placing it firmly in the Execute category. Misuse could trigger unintended UI actions on a connected device.
From the tool's definition Long press at a point on screen. Triggers context menus, selection mode, drag handles, and other long-press behaviors. Implemented as a zero-distance swipe with configurable hold duration.
Attacks that exploit this kind of access
The rule that runs adb_input_long_press 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_input_long_press, this is the rule to start with:
adb_input_long_press 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_input_long_press call is checked against it from then on.
Questions about adb_input_long_press
Long press at a point on screen. Triggers context menus, selection mode, drag handles, and other long-press behaviors. Implemented as a zero-distance swipe with configurable hold duration. 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_input_long_press: 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_input_long_press 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_input_long_press 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_input_long_press. 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_input_long_press 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