idapython_functions_list
AI agents call idapython_functions_list to retrieve information from IDA-doc-hint-mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool appears to list or enumerate IDA Python functions, which is a read-only operation that retrieves information without side effects. No modification, execution, or destructive capability is implied. The empty description reduces confidence slightly, but the naming pattern and context (sibling tool 'get_ida_function_doc') suggests this is a reference/lookup tool for documentation purposes.
From the tool's definition Tool name 'idapython_functions_list' indicates listing/enumerating functions; description is empty but the name suggests a retrieval operation without modification.
Attacks that exploit this kind of access
idapython_functions_list. It is categorised as a Read tool in the IDA-doc-hint-mcp MCP Server, which means it retrieves data without modifying state.
Register the IDA-doc-hint- MCP server in PolicyLayer and add a rule for idapython_functions_list: 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-doc-hint-mcp. Nothing to install.
idapython_functions_list 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 idapython_functions_list 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 idapython_functions_list. 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.
idapython_functions_list is provided by the IDA-doc-hint- MCP server (sysc4lls/ida-doc-hint-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →