AI agents call search_classes_by_keyword 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 searches and retrieves class information from decompiled Android app code without modifying or executing anything. It is a query/retrieval operation with no side effects. Although the tool description is empty, the name and context of other tools strongly indicate it performs a read-only search operation.
From the tool's definition Tool name 'search_classes_by_keyword' indicates a search/query operation. The sibling tools on this server include other Read operations like 'get_all_classes', 'get_android_manifest', 'fetch_current_class', and 'get_cache_stats', all of which retrieve…
Documented attack patterns abuse exactly the kind of access search_classes_by_keyword 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 search_classes_by_keyword:
{
"version": "1",
"default": "deny",
"tools": {
"search_classes_by_keyword": {}
}
}search_classes_by_keyword 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.
search_classes_by_keyword. 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 search_classes_by_keyword: 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.
search_classes_by_keyword 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 search_classes_by_keyword 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 search_classes_by_keyword. 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.
search_classes_by_keyword 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.