Skip to content
Back to search

blueprint-mcp

Diagram generation for understanding codebases and system architecture using Nano Banana Pro.

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/arcadeai--blueprint-mcp/badge.svg)](/listings/arcadeai--blueprint-mcp)

HTML

<a href="/listings/arcadeai--blueprint-mcp"><img src="/api/listings/arcadeai--blueprint-mcp/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

1. Sign up for Arcade

https://arcade.dev

2. Install Dependencies

# Create virtual environment
python3 -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install Arcade CLI
pip install arcade-mcp

3. Login to Arcade

arcade-mcp login

4. Get Google AI Studio API Key

https://aistudio.google.com/ → Create API key

5. Store Secret in Arcade

arcade-mcp secret set GOOGLE_API_KEY="your_api_key_here"

6. Deploy Server

Clone this repo, then:

cd blueprint-mcp
arcade-mcp deploy

7. Create Gateway

1. Go to https://api.arcade.dev/dashboard 2. Click "Gateways" → "Create Gateway" 3. Add your deployed `architect_mcp` server to the gateway

8. Configure Cursor

1. In Cursor: Settings → MCP 2. Add your Arcade gateway URL 3. Restart Cursor

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 149 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # Blueprint MCP
  2. ![Blueprint MCP](images/blueprint-mcp.png)
  3. *Image generated using Blueprint MCP, Nano Banana Pro, and Arcade MCP server.*
  4. Diagram generation for understanding codebases and system architecture using Nano Banana Pro.
  5. **Works with Arcade's ecosystem:** Combine with HubSpot, Google Drive, GitHub, and other Arcade tools to extract data from your systems and visualize it as diagrams.
  6. ## Setup
  7. ### 1. Sign up for Arcade
  8. https://arcade.dev
  9. ### 2. Install Dependencies
  10. ```bash
  11. # Create virtual environment
  12. python3 -m venv venv
  13. source venv/bin/activate # On Windows: venv\Scripts\activate
  14. # Install Arcade CLI
  15. pip install arcade-mcp
  16. ```
  17. ### 3. Login to Arcade
  18. ```bash
  19. arcade-mcp login
  20. ```
  21. ### 4. Get Google AI Studio API Key
  22. https://aistudio.google.com/ → Create API key
  23. ### 5. Store Secret in Arcade
  24. ```bash
  25. arcade-mcp secret set GOOGLE_API_KEY="your_api_key_here"
  26. ```
  27. ### 6. Deploy Server
  28. Clone this repo, then:
  29. ```bash
  30. cd blueprint-mcp
  31. arcade-mcp deploy
  32. ```
  33. ### 7. Create Gateway
  34. 1. Go to https://api.arcade.dev/dashboard
  35. 2. Click "Gateways" → "Create Gateway"
  36. 3. Add your deployed `architect_mcp` server to the gateway
  37. ### 8. Configure Cursor
  38. 1. In Cursor: Settings → MCP
  39. 2. Add your Arcade gateway URL
  40. 3. Restart Cursor
  41. ## Usage
  42. ### Tools
  43. - `start_diagram_job` - Start generation, returns job ID
  44. - `check_job_status` - Check if complete
  45. - `download_diagram` - Download PNG as base64
  46. ### Example Prompts
  47. **Visualize code architecture:**
  48. ```
  49. Analyze the authentication module in src/auth/ and create an
  50. architecture diagram showing the components and their relationships.
  51. ```
  52. **Document API flows:**
  53. ```
  54. Create a sequence diagram showing the OAuth login flow based on
  55. the code in src/auth/oauth.py
  56. ```
  57. **Explain processes:**
  58. ```
  59. Generate a flowchart explaining how our payment processing works,
  60. showing the steps from checkout to confirmation.
  61. ```
  62. **Understand data pipelines:**
  63. ```
  64. Create a data flow diagram for our ETL pipeline showing sources,
  65. transformations, and destinations based on the data/ directory.
  66. ```
  67. **Combine with other Arcade tools:**
  68. ```
  69. Pull the latest deal from HubSpot for "Acme Corp" and create an
  70. architecture diagram of the proposed solution.
  71. ```
  72. ```
  73. Read the system design doc from Google Drive and generate a
  74. visual architecture diagram from it.
  75. ```
  76. ## How It Works
  77. 1. `start_diagram_job` → Returns job ID instantly
  78. 2. Wait 30 seconds (Nano Banana Pro generates)
  79. 3. `check_job_status` → Check if "Complete"
  80. 4. `download_diagram` → Get base64 PNG
  81. 5. Agent decodes and saves to workspace
  82. ---
  83. ## Example Diagrams
  84. ### Enterprise Architecture - Banking Use Case
  85. **Cursor Prompt:**
  86. ```
  87. Can you understand Arcade deeply and create an architecture diagram for someone
  88. who's new and wants to understand Arcade in the broader AI, LLM, and agent landscape?
  89. I want this architecture to fit into a realistic enterprise scenario like a bank,
  90. showcasing how Arcade MCP Runtime fits into their broader architecture.
  91. https://docs.arcade.dev/llms.txt
  92. ```
  93. *Prompt received by Blueprint MCP tool: "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."*
  94. ![Enterprise Banking Architecture](images/arcade_enterprise_banking.png)
  95. ### LangGraph Architecture Learning Card
  96. **Cursor Prompt:**
  97. ```
  98. Help me understand the LangGraph architecture better. I have checked out the
  99. LangGraph codebase here:
  100. /Users/guru/dev/nano/langgraph
  101. Can you do a thorough analysis and help me understand the architecture? I would
  102. love to know details in a visual image: The key components involved, the flows,
  103. and can you create like one fully visual learning card sort of thing that helps
  104. me understand the architecture which I can print and give it to my fellow
  105. architects and help them learn?
  106. ```
  107. *Prompt received by Blueprint MCP tool: "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."*
  108. ![LangGraph Architecture](images/langgraph_architecture_learning_card.png)

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.