[MACD Cross / Crossover / Screening] MACDクロス検出（MACD cross / crossover / golden cross / dead cross / screening）。 pair省略: 複数銘柄スクリーニング / pair指定: 単一ペア深掘り分析（forming検出・過去統計）。 screen（スクリーニング用）: - crossType: golden|dead|both - minHistogramDelta / maxBarsAgo / minReturnPct / maxReturnPct - sortBy: date|hi...
AI agents call detect_macd_cross to retrieve information from Bitbank Lab without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a data analysis and retrieval tool. It screens cryptocurrency market data using technical analysis (MACD indicators) and returns filtered/sorted results. The parameters control filtering and presentation of existing data, not creation or modification of data, not execution of external operations, and not financial actions. It is purely informational/analytical, making it a Read operation with low severity.
From the tool's definition Tool performs MACD cross detection and screening across cryptocurrency pairs. The description indicates it 'analyzes' and 'screens' market data with filtering parameters (crossType, histogram delta, return percentages) and sorting/limiting results.
Attacks that exploit this kind of access
[MACD Cross / Crossover / Screening] MACDクロス検出（MACD cross / crossover / golden cross / dead cross / screening）。 pair省略: 複数銘柄スクリーニング / pair指定: 単一ペア深掘り分析（forming検出・過去統計）。 screen（スクリーニング用）: - crossType: golden|dead|both - minHistogramDelta / maxBarsAgo / minReturnPct / maxReturnPct - sortBy: date|histogram|return|barsAgo - limit: 上位N件. It is categorised as a Read tool in the Bitbank Lab MCP Server, which means it retrieves data without modifying state.
Register the Bitbank Lab MCP server in PolicyLayer and add a rule for detect_macd_cross: 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 Lab. Nothing to install.
detect_macd_cross 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 detect_macd_cross 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 detect_macd_cross. 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.
detect_macd_cross is provided by the Bitbank Lab MCP server (tjackiet/bitbank-genesis-mcp-server-http-archive). 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 →