Extract control flow graph with basic blocks for understanding function logic flow.
AI agents call get_control_flow_graph 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 retrieves and analyzes structural information (control flow graph representation) from already-loaded binaries within Ghidra's analysis environment. It does not modify data, execute arbitrary code, delete anything, or move resources. It is purely an analytical/querying operation that supports reverse engineering comprehension.
From the tool's definition The tool 'get_control_flow_graph' extracts a control flow graph with basic blocks for 'understanding function logic flow.' The verb 'Extract' and the context of analysis for comprehension indicate data retrieval without modification or execution of code.
Documented attack patterns abuse exactly the kind of access get_control_flow_graph 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 get_control_flow_graph:
{
"version": "1",
"default": "deny",
"tools": {
"get_control_flow_graph": {}
}
} get_control_flow_graph 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.
Extract control flow graph with basic blocks for understanding function logic flow. 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 get_control_flow_graph: 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.
get_control_flow_graph 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_control_flow_graph 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_control_flow_graph. 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_control_flow_graph 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.