api-dev-agent-mcp
MCP server that automates the generation of production-grade async FastAPI services following Clean Architecture, with self-healing pytest-based verification and OpenAPI spec ingestion for rapid CRUD API development.
README
š¤ Enterprise Clean-Architecture API Agent (MCP-Powered)
An autonomous, deterministic API Development Agent integrated into VS Code via the Model Context Protocol (MCP). This agent automates the generation of production-grade, asynchronous FastAPI services adhering strictly to Clean Architecture principles, complete with automated test execution and self-healing verification loops.
š Key Features
- Deterministic Code Generation: Employs Jinja2 templating rather than pure LLM generation to guarantee strict standard compliance.
- Clean Architecture Layers: Enforces separation across Model, Schema (DTO), Repository, Service, and Controller layers.
- Model Context Protocol (MCP): Exposes tool execution (
file_ops,openapi_parser,pytest) to GitHub Copilot via lightweight JSON-RPC over STDIO. - Self-Healing Verification Loop: Automatically executes
pytestsuite post-scaffolding and reads stack traces to auto-fix errors. - OpenAPI Spec Ingestion: Parses existing OpenAPI (YAML/JSON) specifications to generate complete CRUD APIs automatically.
šļø Architecture & Technology Stack
- Framework: FastAPI (Async)
- ORM: SQLAlchemy 2.0 (Async Session)
- Validation: Pydantic v2
- Agent Engine: FastMCP / Model Context Protocol
- Templating: Jinja2
- Testing: Pytest &
httpx
Directory Structure
.
āāā .vscode/
ā āāā mcp.json # MCP Server configuration for VS Code
āāā app/
ā āāā controllers/ # FastAPI Routers
ā āāā models/ # SQLAlchemy Database Models
ā āāā repositories/ # Data Access Layer
ā āāā schemas/ # Pydantic Schemas / DTOs
ā āāā services/ # Business Logic Layer
ā āāā main.py # Application Entrypoint & Router Discovery
āāā mcp_server/
ā āāā server.py # FastMCP Tools Definition
ā āāā tools/
ā āāā file_ops.py # Template rendering & workspace disk writes
ā āāā openapi_parser.py # OpenAPI YAML/JSON schema parser
āāā templates/ # Jinja2 Standard Boilerplate Templates
āāā tests/ # Generated Pytest Test Suites
āāā .agent.md # VS Code Copilot Custom Agent Prompt & Protocol
āāā requirements.txt # Python dependencies
āāā README.md
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.