Find and analyze IOKit class hierarchies, vtables, and user client interfaces.
AI agents call find_iokit_classes to retrieve information from Kawaiidra 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 of IOKit kernel driver interfaces by reading binary metadata (class hierarchies, virtual method tables, user client interfaces). It retrieves and examines data structures within a binary without modifying code, executing arbitrary operations, or deleting anything. The operations are read-only reconnaissance typical of reverse engineering analysis tools.
From the tool's definition Tool name 'find_iokit_classes' and description 'Find and analyze IOKit class hierarchies, vtables, and user client interfaces' indicate retrieval and analysis of existing binary structures without modification or execution.
Documented attack patterns abuse exactly the kind of access find_iokit_classes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Kawaiidra MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for find_iokit_classes:
{
"version": "1",
"default": "deny",
"tools": {
"find_iokit_classes": {}
}
} find_iokit_classes 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 and analyze IOKit class hierarchies, vtables, and user client interfaces. It is categorised as a Read tool in the Kawaiidra MCP MCP Server, which means it retrieves data without modifying state.
Register the Kawaiidra MCP server in PolicyLayer and add a rule for find_iokit_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 Kawaiidra MCP. Nothing to install.
find_iokit_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 find_iokit_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 find_iokit_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.
find_iokit_classes is provided by the Kawaiidra MCP server (wagonbomb/kawaiidra-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Kawaiidra MCP, 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.
94 Kawaiidra MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.