AI agents call find_paths to retrieve information from Ida Domain 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 existing data (execution paths in a disassembled binary) without modifying, deleting, or executing code. It is analogous to a search or query operation on the reverse engineering database. The worst-case misuse would be unauthorized information disclosure about program control flow, which has low blast radius compared to destructive or execution-based tools.
From the tool's definition Tool performs path-finding analysis between addresses in a reverse engineering context. No modification of data, deletion, code execution, or financial operations. The tool 'find_paths' queries and retrieves execution paths from the IDA Pro database.
Documented attack patterns abuse exactly the kind of access find_paths gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Ida Domain, and nothing reaches the server without passing your rules. This is the rule we recommend for find_paths:
{
"version": "1",
"default": "deny",
"tools": {
"find_paths": {}
}
}find_paths 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 execution paths between source and target addresses. It is categorised as a Read tool in the Ida Domain MCP Server, which means it retrieves data without modifying state.
Register the Ida Domain MCP server in PolicyLayer and add a rule for find_paths: 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 Ida Domain. Nothing to install.
find_paths 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_paths 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_paths. 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_paths is provided by the Ida Domain MCP server (xxyyue/ida_domain_mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Ida Domain, 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.
74 Ida Domain tools catalogued and risk-classified — across an index of 43,000+ MCP servers.