android_shell
Run an allowlisted shell command on the Android device. First element of cmd array must be allowlisted: input, pm, dumpsys, am, getprop, screencap, monkey, uiautomator, settings, wm, cmd, content, ls, cat, pidof, ps, echo, service.
This record as markdown: /tools/io-github-saloprj-dialogbrain/android-shell.md
What android_shell does on Dialogbrain
AI agents invoke android_shell to trigger actions in Dialogbrain. 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.
| Parameter | Type | Required | Description |
|---|---|---|---|
cmd | string | Yes | Shell command to run (array form preferred, space-separated accepted). Example: 'getprop ro.build.version.release' or ['getprop', 'ro.build.version.release'] |
channel_account_id | integer | — | Android device channel_account ID. Omit when the workspace has a single Android device; REQUIRED when it has more than one (e.g. WhatsApp + LINE), else the call |
Parameters from the server's own tool schema.
Why android_shell is rated High
android_shell triggers real processes with real consequences. An agent gone sideways doesn't fire it once. It starts dozens of builds, sends mass notifications, or burns through compute before anyone looks up.
Risk signalsAccepts freeform code/query input (cmd)
Attacks that exploit this kind of access
The rule that runs android_shell safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Dialogbrain, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For android_shell, this is the rule to start with:
android_shell 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 Dialogbrain, apply this rule, and every android_shell call is checked against it from then on.
Questions about android_shell
Run an allowlisted shell command on the Android device. First element of cmd array must be allowlisted: input, pm, dumpsys, am, getprop, screencap, monkey, uiautomator, settings, wm, cmd, content, ls, cat, pidof, ps, echo, service. It is categorised as a Execute tool in the Dialogbrain MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
android_shell accepts 2 parameters: cmd, channel_account_id. Required: cmd. The full parameter table on this page comes from the server's own tool schema.
Register the Dialogbrain MCP server in PolicyLayer and add a rule for android_shell: 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 Dialogbrain. Nothing to install.
android_shell 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 android_shell 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 android_shell. 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.
android_shell is provided by the Dialogbrain MCP server (https://api.dialogbrain.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Dialogbrain, and thousands of servers like it.
Across the catalogue