AI agents invoke py_eval to trigger actions in Ida Domain. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool allows execution of arbitrary Python code within IDA Pro, a powerful reverse engineering platform. An AI agent with access to py_eval could execute malicious code, modify binaries, exfiltrate data, or compromise the analysis environment.
From the tool's definition Tool name 'py_eval' combined with description 'Execute Python code in IDA context' explicitly indicates arbitrary code execution capabilities within IDA Pro's environment.
Documented attack patterns abuse exactly the kind of access py_eval 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 py_eval:
{
"version": "1",
"default": "deny",
"tools": {
"py_eval": {
"limits": [
{
"counter": "py_eval_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}py_eval stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Execute Python code in IDA context. It is categorised as a Execute tool in the Ida Domain MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Ida Domain MCP server in PolicyLayer and add a rule for py_eval: 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.
py_eval is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the py_eval 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 py_eval. 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.
py_eval 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.