Check system dependencies required for decompilation.
AI agents call check_dependencies to retrieve information from Android Reverse Engineering without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a Read operation as it retrieves information about system dependencies without side effects. The severity is low because checking dependencies has no blast radius—it cannot corrupt data, execute code, delete files, or move money. Even in a misuse scenario, a malicious agent could only learn what dependencies are installed, which is low-risk reconnaissance.
From the tool's definition The tool "check_dependencies" performs a diagnostic read operation to verify the presence and status of system dependencies required for decompilation.
Documented attack patterns abuse exactly the kind of access check_dependencies gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Android Reverse Engineering, and nothing reaches the server without passing your rules. This is the rule we recommend for check_dependencies:
{
"version": "1",
"default": "deny",
"tools": {
"check_dependencies": {}
}
}check_dependencies is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Check system dependencies required for decompilation. It is categorised as a Read tool in the Android Reverse Engineering MCP Server, which means it retrieves data without modifying state.
Register the Android Reverse Engineering MCP server in PolicyLayer and add a rule for check_dependencies: 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 Reverse Engineering. Nothing to install.
check_dependencies 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 check_dependencies 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 check_dependencies. 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.
check_dependencies is provided by the Android Reverse Engineering MCP server (vichhka-git/android-reverse-engineering-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Android Reverse Engineering, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
6 Android Reverse Engineering tools catalogued and risk-classified — across an index of 43,000+ MCP servers.