Backend Architect MCP Server

Backend Architect MCP Server

An expert MCP toolchain designed to act as a Backend Architect for AI agents. This server enforces a strict "Atomic Development" workflow for building Python FastAPI + Supabase backends.

🚀 Overview

The Backend Architect server guides an agent through a Plan -> Prompt -> Write loop, ensuring that database models, API routes, and tests are built in the correct dependency order.

Key Features

• Atomic Development: Focuses on one component at a time.
• Workflow Enforcement: Models → Routes → Tests (respects model dependencies).
• Auto-Imports: Automatically updates __init__.py files for models and routes.
• State Persistence: Maintains .mcp_state.json to track building progress.
• Contextual Prompts: Generates specialized system prompts for each component.

🛠️ Tech Stack

• Python 3.12
• MCP SDK (FastMCP)
• UV (Dependency Manager)
• Pydantic (State Validation)

📦 Installation

Ensure you have uv installed. Then, clone the repository and install dependencies:

# Clone the repository
cd mcp_fastapi

# Install dependencies and run the server
uv run server.py

🛠️ Tools Reference

1. Initialization

• initialize_project(root_path: str = "."): Scaffolds the FastAPI project structure and pyproject.toml. Defaults to the current working directory.

2. Planning

• save_roles_plan(roles: list): Define user roles and permissions.
• save_database_plan(models: list): Define SQLModel schemas and relationships.
• save_route_plan(routes: list): Define API endpoints and methods.
• save_test_plan(tests: list): Define simulation scenarios.

3. Execution

• get_next_pending_task(): The "Traffic Cop" that tells you exactly what to build next.
• get_file_instruction(task_type: str, task_name: str): Returns a strict system prompt for the AI to follow.
• write_component_file(type: str, name: str, content: str): Writes the code and marks the task as "done".

🔄 The Loop

1. Initialize: Set up your project root.
2. Plan: Feed the architect your schemas and endpoints.
3. Draft: Ask get_next_pending_task() for the current objective.
4. Learn: Get instructions via get_file_instruction().
5. Write: Submit code via write_component_file().
6. Repeat: Until the entire backend is architected.

⚙️ MCP Configuration

Add this to your MCP settings file (e.g., mcp_config.json or your IDE's MCP settings):

{
  "mcpServers": {
    "backend-architect": {
      "command": "uv",
      "args": [
        "run",
        "--project",
        "/path/to/server/directory",
        "python",
        "server.py"
      ]
    }
  }
}

[!TIP] Use the absolute path to the directory where you cloned this repository for the --project argument. This ensures the server can find its dependencies regardless of where your AI agent is currently working.

Built with ❤️ for the AI-First Developer.