Back to MCP directory
publicPublicdnsLocal runtime

blueprint-mcp

Blueprint MCP是一个基于Arcade生态的图表生成工具,利用Nano Banana Pro等技术,通过分析代码库和系统架构自动生成架构图、流程图等可视化图表,帮助开发者理解复杂系统。

article

README

🚀 Blueprint MCP

Blueprint MCP 借助 Nano Banana Pro 实现代码库和系统架构的可视化图表生成,帮助你更好地理解代码和系统架构。它可以与 Arcade 的生态系统集成,与 HubSpot、Google Drive、GitHub 等工具结合,从你的系统中提取数据并将其可视化为图表。

🚀 快速开始

✨ 主要特性

  • 利用 Nano Banana Pro 生成图表,助力理解代码库和系统架构。
  • 与 Arcade 生态系统兼容,可结合多种工具提取数据并可视化。

📦 安装指南

1. 注册 Arcade

访问链接:https://arcade.dev

2. 安装依赖

# 创建虚拟环境
python3 -m venv venv
source venv/bin/activate  # 在 Windows 上:venv\Scripts\activate

# 安装 Arcade CLI
pip install arcade-mcp

3. 登录 Arcade

arcade-mcp login

4. 获取 Google AI Studio API 密钥

访问:https://aistudio.google.com/ ,创建 API 密钥。

5. 在 Arcade 中存储密钥

arcade-mcp secret set GOOGLE_API_KEY="your_api_key_here"

6. 部署服务器

cd architect_mcp
arcade-mcp deploy

7. 创建网关

  1. 访问:https://api.arcade.dev/dashboard
  2. 点击 “Gateways” → “Create Gateway”
  3. 将已部署的 architect_mcp 服务器添加到网关

8. 配置 Cursor

  1. 在 Cursor 中:Settings → MCP
  2. 添加你的 Arcade 网关 URL
  3. 重启 Cursor

💻 使用示例

基础用法

工具

  • start_diagram_job - 开始生成图表,返回作业 ID
  • check_job_status - 检查作业是否完成
  • download_diagram - 以 base64 格式下载 PNG 图表

示例提示

可视化代码架构

Analyze the authentication module in src/auth/ and create an 
architecture diagram showing the components and their relationships.

记录 API 流程

Create a sequence diagram showing the OAuth login flow based on 
the code in src/auth/oauth.py

解释流程

Generate a flowchart explaining how our payment processing works,
showing the steps from checkout to confirmation.

理解数据管道

Create a data flow diagram for our ETL pipeline showing sources,
transformations, and destinations based on the data/ directory.

与其他 Arcade 工具结合

Pull the latest deal from HubSpot for "Acme Corp" and create an
architecture diagram of the proposed solution.
Read the system design doc from Google Drive and generate a 
visual architecture diagram from it.

🔧 技术细节

  1. 调用 start_diagram_job 后会立即返回作业 ID。
  2. 等待 30 秒(Nano Banana Pro 进行生成操作)。
  3. 调用 check_job_status 检查作业是否 “Complete”。
  4. 调用 download_diagram 获取 base64 格式的 PNG 图表。
  5. 代理会对图表进行解码并保存到工作区。

示例图表

企业架构 - 银行用例

Cursor 提示

Can you understand Arcade deeply and create an architecture diagram for someone 
who's new and wants to understand Arcade in the broader AI, LLM, and agent landscape? 
I want this architecture to fit into a realistic enterprise scenario like a bank, 
showcasing how Arcade MCP Runtime fits into their broader architecture.

https://docs.arcade.dev/llms.txt

Blueprint MCP 工具接收到的提示:“Create enterprise architecture diagram with 5 layers: LAYER 1 End Users (Customer Service Agents, Loan Officers, Compliance Team, IT Ops), LAYER 2 Banking AI Assistant (Cursor IDE / Custom UI), LAYER 3 AI Layer showing GPT-4/Claude and LangChain/CrewAI (Model-Agnostic), LAYER 4 Arcade MCP Runtime (large box) containing Runtime Components (MCP Gateway, Tool Registry, OAuth 2.0 Auth, Secret Management, Session Manager) AND Hosted MCP Servers section with 6 MCP servers (Salesforce, Email/Gmail, Slack, Database, Document, Custom Banking) ALL INSIDE the Arcade box, LAYER 5 Bank's Existing Infrastructure (Core Banking System, CRM Salesforce, Compliance Database, Document Repository, Communication Systems, Legacy APIs). Show data flow arrows with labels (Tool Calls, Authenticated Requests, API Calls). Use technical whiteboard style, muted colors (gray, light blue, purple, orange), monospace fonts, 16:9.”

Enterprise Banking Architecture

LangGraph 架构学习卡

Cursor 提示

Help me understand the LangGraph architecture better. I have checked out the 
LangGraph codebase here:

/Users/guru/dev/nano/langgraph

Can you do a thorough analysis and help me understand the architecture? I would 
love to know details in a visual image: The key components involved, the flows, 
and can you create like one fully visual learning card sort of thing that helps 
me understand the architecture which I can print and give it to my fellow 
architects and help them learn?

Blueprint MCP 工具接收到的提示:“Create LangGraph architecture learning card with 6 sections: Core Components (State, Nodes, Edges with flow diagram), StateGraph Class workflow (Define → Build → Compile → Execute), Pregel-Inspired Execution showing super-steps with parallel/sequential execution examples, Checkpointing System (BaseCheckpointSaver, checkpoint-postgres/sqlite, state snapshots flow), Monorepo Structure (langgraph core, prebuilt, checkpoint libs, cli, sdk-py, sdk-js), and Capabilities (Durable execution, Human-in-the-loop, Memory, Streaming, Multi-agent, Sub-graphs). Use technical whiteboard style, muted colors (blue, gray, purple, green, orange), monospace fonts for code terms, information-dense layout, 16:9, printable quality.”

LangGraph Architecture

help

Runtime guide

cloud

Hosted runtime

Hosted servers run from a provider-managed environment. You usually connect the MCP client to the hosted endpoint or follow the provider's authorization flow, without keeping a local process alive

  1. Open provider connection page
  2. Authorize or copy endpoint
  3. Connect from your MCP client
terminal

Local runtime / other methods

Local servers run on your own machine or infrastructure. You normally copy the server_config into your MCP client, install the required package, and provide env variables from env_schema when needed

  1. Copy server_config
  2. Install required package
  3. Fill env variables and restart client