AI agents call get_xrefs_to_class 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 search/query operation on decompiled code to find cross-references to a class. It retrieves information about code relationships without side effects—no data is created, modified, deleted, or executed. It aligns with the 'Read' category (retrieve or query data; no side effects). In the context of JADX reverse engineering, this is purely an analytical tool used to understand code dependencies.
From the tool's definition Tool name 'get_xrefs_to_class' and description 'Find all references to a class' indicate a query operation that retrieves cross-reference data. This is a read-only operation that searches for and lists references without modifying any data.
Documented attack patterns abuse exactly the kind of access get_xrefs_to_class 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_xrefs_to_class:
{
"version": "1",
"default": "deny",
"tools": {
"get_xrefs_to_class": {}
}
}get_xrefs_to_class 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.
Find 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_xrefs_to_class: 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_xrefs_to_class 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_xrefs_to_class 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_xrefs_to_class. 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_xrefs_to_class is provided by the JADX-MCP-SERVER MCP server (zinja-coder/jadx-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 32 JADX-MCP-SERVER tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
32 JADX-MCP-SERVER tools catalogued and risk-classified — across an index of 42,500+ MCP servers.