android_files
AI agents call android_files to retrieve information from Android MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Without description, classification relies on naming convention and context. 'android_files' most likely provides file listing, reading, or retrieval capabilities (Read category). However, the empty description and the presence of other powerful sibling tools ('android_system', 'android_automation') creates ambiguity about whether this tool also enables file creation, modification, or deletion.
From the tool's definition Tool name 'android_files' with empty description suggests file system access/retrieval operations typical of Android file management tools, and positioned among tools like 'android_screen', 'android_app', 'android_interact' which are Read or Execute in nature.
Attacks that exploit this kind of access
android_files. It is categorised as a Read tool in the Android MCP MCP Server, which means it retrieves data without modifying state.
Register the Android MCP server in PolicyLayer and add a rule for android_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 Android MCP. Nothing to install.
android_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 android_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 android_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.
android_files is provided by the Android MCP server (steph-ux/android-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 →