Automata MCP Server
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Automata MCP Serverlist all available tools"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Automata-mcp-server
一个基于 FastAPI 和 Model Context Protocol (MCP) 的插件化服务器。
功能特性
🔌 插件化架构,支持动态加载工具
🔄 热重载功能,开发时自动监听代码变化并重启服务器
🚀 基于 FastAPI,高性能异步处理
🔐 支持 API Key 认证
📦 支持自动安装工具依赖
Related MCP server: my-mcp-server2
快速开始
1. 安装依赖
使用 uv(推荐):
uv sync或使用 pip:
pip install -r requirements.txt📝 依赖管理说明:
所有依赖在
pyproject.toml中管理requirements.txt由pyproject.toml自动生成Git pre-commit 钩子会自动同步两个文件
2. 配置环境变量
复制示例配置文件并修改:
cp .env.example .env编辑 .env 文件,设置必要的配置项:
HOST=localhost
PORT=8000
AUTOMATA_API_KEY=your_api_key_here3. 启动服务器
开发模式(启用热重载)
使用 uv:
uv run main.py或直接运行:
python main.py服务器将在开发模式下启动,自动监听项目中所有 Python 文件的变化。当检测到 .py 文件修改时,服务器会自动重启,无需手动重启。
生产模式(禁用热重载)
如需在生产环境中运行,可以直接使用 uvicorn:
uvicorn app.server:app --host $HOST --port $PORT开发说明
热重载功能
服务器默认启用热重载功能,会监听项目中所有 Python 文件(**/*.py)的变化。当任何 .py 文件发生变化时,服务器会自动重启并加载最新代码。
详细的开发指南请查看:docs/development.md
添加新工具
在
src/或app/AutoUp-MCP-Extension/目录下创建新的工具包继承
BaseMCPTool类并实现工具逻辑添加
config.yaml配置文件服务器会自动发现并加载新工具(开发模式下会自动重载)
API 文档
启动服务器后,访问以下地址查看自动生成的 API 文档:
Swagger UI: http://localhost:8000/docs
ReDoc: http://localhost:8000/redoc
项目结构
.
├── app/ # 核心应用代码
│ ├── server.py # 服务器主文件
│ ├── base_tool.py # 工具基类
│ ├── routers.py # 路由定义
│ └── AutoUp-MCP-Extension/ # 扩展工具目录
├── src/ # 用户工具目录
│ └── fetch/ # 示例工具
├── main.py # 入口文件
├── pyproject.toml # 项目配置
├── .env.example # 环境变量示例
└── README.md # 项目说明许可证
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
Nifty's MCP server — exposes tasks, projects, messages, and files as tools for AI agents.
MCP server for progressive tool usage at any scale (see https://klavis.ai)
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
MCP server for OpenAI API (chat completions, image generation, embeddings) via AceDataCloud
Related MCP Servers
- FlicenseNot gradedqualityFmaintenanceA production-ready MCP server built with FastAPI, providing an enhanced tool registry for creating, managing, and documenting AI tools for Large Language Models (LLMs).34-
- FlicenseNot gradedqualityDmaintenanceA Model Context Protocol server built with FastMCP that features dynamic tool loading and modular management via a dedicated tool directory. It supports both stdio and HTTP transport modes, enabling efficient development and deployment of custom MCP tools.-
- FlicenseNot gradedqualityDmaintenanceA Python-based MCP server that exposes tools over streamable HTTP using FastAPI, enabling connection to AI assistants like Cursor. Supports multiple servers mounted in a single FastAPI app.-
- FlicenseNot gradedqualityDmaintenanceA FastAPI + FastMCP integrated template for quickly building MCP servers that expose custom business logic as AI-accessible tools.-