Get the current call state (idle, ringing, or offhook)
AI agents call adb_call_state to retrieve information from Openclaw Adb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and returns the current telephony state of an Android device. It has no capacity to modify data, execute commands, delete information, or commit financial transactions. While the MCP server overall enables device control, this specific tool is purely informational.
From the tool's definition Tool name 'adb_call_state' and description 'Get the current call state (idle, ringing, or offhook)' indicate a query operation that retrieves device state without modifying, executing external actions, or creating side effects.
Attacks that exploit this kind of access
Get the current call state (idle, ringing, or offhook). It is categorised as a Read tool in the Openclaw Adb MCP Server, which means it retrieves data without modifying state.
Register the Openclaw Adb MCP server in PolicyLayer and add a rule for adb_call_state: 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 Openclaw Adb. Nothing to install.
adb_call_state is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the adb_call_state 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_call_state. 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_call_state is provided by the Openclaw Adb MCP server (wilsonbeam/openclaw-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 →