List files in a directory on the device
AI agents call adb_list_files to retrieve information from ADB MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves directory contents without side effects. It is a read-only query operation comparable to 'ls' or 'dir'. While the ADB server as a whole includes destructive tools (install_app, shell command execution), this specific tool only lists files and poses minimal risk if misused by an agent—the worst outcome is unauthorized information disclosure about device filesystem structure.
From the tool's definition Tool name 'adb_list_files' and description 'List files in a directory on the device' indicate a file listing operation with no modification or deletion.
Attacks that exploit this kind of access
List files in a directory on the device. It is categorised as a Read tool in the ADB MCP Server MCP Server, which means it retrieves data without modifying state.
Register the ADB MCP Server MCP server in PolicyLayer and add a rule for adb_list_files: 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_list_files 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_list_files 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_list_files. 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_list_files is provided by the ADB MCP Server MCP server (richard0913/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 →