Extract call hierarchy showing function relationships. Returns a tree/graph of which functions call which other functions.
AI agents call get_call_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.
The tool queries and retrieves static analysis information (call graph data) from an already-analyzed binary. It performs no code execution, data modification, deletion, or financial operations. This is a straightforward Read operation that has no side effects on the binary or the system. The low severity reflects that viewing call relationships poses minimal risk even if misused by an agent.
From the tool's definition Tool description states it 'Extract[s] call hierarchy' and 'Returns a tree/graph of which functions call which other functions.' The verb 'extract' and 'returns' indicate read-only retrieval of analysis results without modification or execution of code.
Documented attack patterns abuse exactly the kind of access get_call_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_call_graph:
{
"version": "1",
"default": "deny",
"tools": {
"get_call_graph": {}
}
}get_call_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 call hierarchy showing function relationships. Returns a tree/graph of which functions call which other functions. 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_call_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_call_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_call_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_call_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_call_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.