AI agents call get_class_xrefs to retrieve information from Jadx MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a read-only operation that queries and returns information about code structure. It is analogous to a search or grep operation over decompiled Java/Android source code. There are no destructive, modifying, or execution capabilities involved. The blast radius of misuse is limited to information disclosure.
From the tool's definition Tool name 'get_class_xrefs' and description 'Returns all references to a class' indicate a query/lookup operation. No side effects, no data modification, no code execution, and no deletion. It retrieves cross-reference information from decompiled code.
Documented attack patterns abuse exactly the kind of access get_class_xrefs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Jadx MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_class_xrefs:
{
"version": "1",
"default": "deny",
"tools": {
"get_class_xrefs": {}
}
}get_class_xrefs 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.
Returns all references to a class. It is categorised as a Read tool in the Jadx MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Jadx MCP Server MCP server in PolicyLayer and add a rule for get_class_xrefs: 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 Jadx MCP Server. Nothing to install.
get_class_xrefs 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 get_class_xrefs 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 get_class_xrefs. 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.
get_class_xrefs is provided by the Jadx MCP Server MCP server (mobilehackinglab/jadx-mcp-plugin). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Jadx MCP Server, 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.
13 Jadx MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.