ibkr_headless_mcp

The server correctly externalizes sensitive IBKR OAuth credentials into environment variables and separate files. There are no obvious 'eval' or 'exec' calls within the provided source code, reducing direct code injection risks. The primary security consideration is the potential for an unconstrained LLM agent to make unauthorized data retrieval requests through the `call_endpoint` tool, as it directly passes agent-provided `path` and `params` to the `ibind` client's GET method. However, since `call_endpoint` exclusively uses `client.get` and the documented endpoints are read-only, the risk of malicious write operations (e.g., placing trades) appears mitigated by the current implementation which is restricted to GET requests.