Get all IDAPython functions.
AI agents call idapython_functions 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 retrieves or lists available IDAPython functions, which is a read-only query operation. It does not modify, execute, or delete anything. The blast radius of misuse is minimal since it only exposes documentation/API information about what functions are available in IDAPython, which is already public knowledge for users with IDA access.
From the tool's definition Tool name is 'idapython_functions' and description states 'Get all IDAPython functions' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Get all IDAPython functions. 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: 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 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 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. 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 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 →