Enterprise MCP Server Template

Enterprise MCP Server Template

A production-ready, transport-independent foundation for building enterprise MCP servers in Python. Provides infrastructure, configuration, DI, logging, and tooling so downstream projects can focus on domain capabilities.

Category
访问服务器

README

Enterprise MCP Server Template

A production-ready, transport-independent foundation for building enterprise Model Context Protocol (MCP) servers in Python.

This template contains zero business logic. It provides the infrastructure, abstractions, and tooling that every MCP server needs, so downstream projects can focus on their domain capabilities.

Template First Principle All new MCP servers must be created from this template. Generic capabilities are added to the template; server-specific capabilities remain in the individual repository. The template evolves independently, and downstream projects adopt new template versions through controlled upgrades.


Features

  • Transport-independent core — Streamable HTTP (default), SSE, and stdio behind a single Transport abstraction. Business logic never depends on a concrete transport.
  • Configuration — hierarchical loading: bundled defaults → environment YAML → environment variables → CLI overrides (Pydantic v2 + YAML).
  • Dependency injection — small, testable async-capable DI container.
  • Structured logging — structlog with JSON and console renderers.
  • Event bus — async-first publish/subscribe with subscriber isolation.
  • Tool framework — @tool decorator, metadata models, registry, and input validation.
  • Extendable scaffolds — plugins, middleware, hooks, providers, workers, persistence, security, and AI packages with defined extension points.
  • Plugin framework — minimal plugin architecture with manifest-based discovery, lifecycle hooks, and a unified PluginContext.
  • Form Automation plugin — deterministic DOM-based form detection, pre-interaction validation, and structured form tools (fill, check, uncheck, select, submit).
  • Observable — /health, /live, /ready, /version endpoints.
  • Developer tooling — uv, Ruff, Pyright, pytest, pre-commit, Makefile.
  • Operations — Docker, docker-compose, Kubernetes manifests, GitHub Actions.

Technology Stack

Concern Choice
Python 3.13
Package manager uv
Web framework FastAPI
MCP SDK Official Python MCP SDK
Validation Pydantic v2
Config pydantic-settings + YAML
Logging structlog
CLI Typer
HTTP server Uvicorn
Testing pytest
Async asyncio
Lint Ruff
Type checking Pyright
Hooks pre-commit
Docs MkDocs Material
Containers Docker
Plugins Built-in framework
Form Automation Deterministic DOM + Retry

Quick Start

Prerequisites: uv with Python 3.13.

uv sync --all-extras
make doctor        # verify the environment
make test          # run the test suite
make run           # start the server (http://localhost:8000)

Check the server is healthy:

curl http://localhost:8000/health
curl http://localhost:8000/ready
curl http://localhost:8000/version

CLI

uv run enterprise-mcp serve            # run the server
uv run enterprise-mcp version          # print version info
uv run enterprise-mcp doctor           # environment diagnostics
uv run enterprise-mcp config --json    # show effective configuration
uv run enterprise-mcp plugins          # list extensions (scaffold)

Repository Layout

src/enterprise_mcp/
├── foundation/     # DI container, app lifecycle, startup/shutdown
├── config/         # loaders, defaults, settings/*.yaml
├── observability/  # logging, metrics, tracing
├── security/       # auth, RBAC, secrets, audit
├── transport/      # base interface, HTTP, SSE, stdio
├── mcp/            # protocol and server abstractions
├── tools/          # decorators, metadata, loader, validator, registry
├── extensions/     # plugins, middleware, hooks, providers
├── workers/        # executors, schedulers, queues, retry
├── persistence/    # repositories, models, migrations, database
├── interfaces/     # REST, WebSocket, internal API
├── events/         # event bus
├── resources/      # templates, static, sample-data
├── utils/          # shared utilities
├── ai/             # memory, prompts, agents (reserved)
└── cli/            # Typer-based CLI

Documentation

License

MIT — see LICENSE.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选