Type text into focused input. ASCII via key injection, Unicode via clipboard paste (Android 10+).
AI agents invoke adb_text 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 simulates user input by injecting keystrokes or pasting clipboard content into the focused input on an Android device. It triggers external operations (input simulation on a real device) that depend on the text argument, which could be used to submit forms, send messages, or interact with apps in ways that have side effects. It's not purely Read or Write of data — it executes device-level input actions.
From the tool's definition Type text into focused input. ASCII via key injection, Unicode via clipboard paste
Attacks that exploit this kind of access
Type text into focused input. ASCII via key injection, Unicode via clipboard paste (Android 10+). 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_text: 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_text 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_text 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_text. 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_text is provided by the ADB MCP Server MCP server (lll-404/adb-mcp-server). 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 →