AI agents use declare_stack to create or update resources in Ida Domain — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ida Domain environment.
This tool creates or declares stack variables, which modifies the analysis metadata stored in the IDA Pro database. Such modifications are reversible (variables can be removed or re-declared), and the operation is scoped to local analysis context rather than destructive deletion or arbitrary code execution.
From the tool's definition Tool name 'declare_stack' and description 'Create stack vars' indicate modification of stack variable declarations within IDA Pro's reverse engineering database.
Documented attack patterns abuse exactly the kind of access declare_stack 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 declare_stack:
{
"version": "1",
"default": "deny",
"tools": {
"declare_stack": {
"limits": [
{
"counter": "declare_stack_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}declare_stack stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Create stack vars. It is categorised as a Write tool in the Ida Domain MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ida Domain MCP server in PolicyLayer and add a rule for declare_stack: 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.
declare_stack is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the declare_stack 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 declare_stack. 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.
declare_stack 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.