// MCP TOOL REFERENCE

BLUEMOUSE TOOLS

8 tools from the Bluemouse MCP Server, categorised by risk level.

// ALL 8 BLUEMOUSE TOOLS

READ 2 tools

Read analyze_requirement_trap 分析用戶需求並檢測是否需要蘇格拉底面試檢測需求中的模糊點、邏輯漏洞和潛在災難場景，如果發現問題則自動生成蘇格拉底式問題。 Args: user_inp... Read check_bluemouse_environment 檢查藍圖小老鼠運行環境檢測宿主環境（Antigravity/Cursor/VSCode）、API Key配置和依賴狀態。 Returns: JSON 格式的環境...

WRITE 5 tools

Write deliver_bluemouse_project 將生成的項目文件寫入宿主工作區完成從「寄生」到「交付」的完整閉環。 Args: project_name: 項目名稱 files: 文件映射 (... Write record_socratic_answers 記錄蘇格拉底面試的答案到 data_trap.jsonl 用於訓練數據收集（如果用戶允許）。 Args: requirement: 原始需求 qu... Write mmla_create_node Create a new node in the architecture. 'spec' should be a JSON string defining inputs/outputs/constraints. Write mmla_update_status mmla_update_status Write open_bluemouse_ui open_bluemouse_ui

EXECUTE 1 tools

Execute mmla_validate_code Validate code against MMLA specification. 🚨 核心修正 1: 絕對門禁檢查只有狀態為 GREEN 的節點才能進行代碼驗證 A...

// FAQ

How many tools does the Bluemouse MCP server have? +

The Bluemouse MCP server exposes 8 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Bluemouse tools? +

Route the Bluemouse server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard; they are enforced on every call before it reaches the server.

What risk categories do Bluemouse tools fall into? +

Bluemouse tools are categorised as Read (2), Write (5), Execute (1). Each category has a recommended default policy.

Enforce policy on every Bluemouse tool call.

Deterministic rules across all 8 Bluemouse tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN BLUEMOUSE →

Free to start. No card required.

42,500+ MCP servers and 110,000+ tools scanned and risk-classified.