read_project_file
AI agents call read_project_file to retrieve information from Android source code without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves file contents from a validated Android project without creating, modifying, or deleting data. It is a read-only operation with minimal blast radius. The validation mechanism (gradle file checking) and sibling tools (read_multiple_project_files, validate_android_project, get_all_project_files) all confirm a read-focused scope. Despite the empty description, the context and naming are clear.
From the tool's definition Server purpose is to 'browse and read Android project files' and tool name is 'read_project_file', indicating file retrieval with no modification.
Attacks that exploit this kind of access
read_project_file. It is categorised as a Read tool in the Android source code MCP Server, which means it retrieves data without modifying state.
Register the Android source code MCP server in PolicyLayer and add a rule for read_project_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 Android source code. Nothing to install.
read_project_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 read_project_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 read_project_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.
read_project_file is provided by the Android source code MCP server (sdilogin/filesystem-android). 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 →