AI agents call get_margin_positions to retrieve information from Bitbank without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Even though get_margin_positions only reads data, uncontrolled read access leaks sensitive information and racks up API costs — an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
[Margin Positions / 信用建玉一覧] 信用取引の保有建玉一覧（通貨ペア・方向・数量・評価額・平均取得価格）を取得。追証・不足金がある場合はアラート表示。通貨ペアでフィルタ可能。Private API。. It is categorised as a Read tool in the Bitbank MCP Server, which means it retrieves data without modifying state.
Register the Bitbank MCP server in PolicyLayer and add a rule for get_margin_positions: 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 Bitbank. Nothing to install.
get_margin_positions 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 get_margin_positions 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 get_margin_positions. 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.
get_margin_positions is provided by the Bitbank MCP server (tjackiet/bitbank-lab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.