List class names from various languages (C++, ObjC, Swift, Java, Dalvik).
AI agents call Radare2_list_classes to retrieve information from Reversecore_MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs static analysis to extract and list class definitions from compiled code. It retrieves information only—class names are metadata that can be read from binaries without side effects, code execution, or data modification. While reverse engineering itself may have security implications in certain contexts, the tool's function is fundamentally a read operation (list/query).
From the tool's definition Tool name 'Radare2_list_classes' and description 'List class names from various languages' indicates a retrieval operation that enumerates metadata from binaries without modification or execution.
Attacks that exploit this kind of access
List class names from various languages (C++, ObjC, Swift, Java, Dalvik). It is categorised as a Read tool in the Reversecore_MCP MCP Server, which means it retrieves data without modifying state.
Register the Reversecore_ MCP server in PolicyLayer and add a rule for Radare2_list_classes: 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 Reversecore_MCP. Nothing to install.
Radare2_list_classes 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 Radare2_list_classes 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 Radare2_list_classes. 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.
Radare2_list_classes is provided by the Reversecore_ MCP server (sjkim1127/reversecore_mcp). 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 →