Pull a file from device to local system
AI agents call adb_pull_file 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 files from a device to a local system, which is fundamentally a read operation with no side effects on the source. However, severity is rated high rather than low because: (1) it could exfiltrate sensitive data (credentials, private messages, photos, personal information) from an Android device, creating significant privacy and security risks; (2) the blast radius depends on what files an agent…
From the tool's definition Tool name 'adb_pull_file' and description 'Pull a file from device to local system' indicate retrieval of data from an Android device without modification or deletion.
Attacks that exploit this kind of access
Pull a file from device to local system. 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_pull_file: 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_pull_file 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_pull_file 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_pull_file. 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_pull_file 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 →