Template MCP Server
A production-ready template for building Model Context Protocol servers in Python, featuring example tools, structured logging, and multiple transport protocols.
README
Template MCP Server
A production-ready template for developing Model Context Protocol (MCP) servers using Python and FastMCP. This server provides a foundation for creating MCP-compliant servers with comprehensive examples of tools, structured logging, configuration management, and containerized deployment.
The template includes three example MCP tools: a multiply calculator, a code review prompt generator, and a Red Hat logo tool. It demonstrates best practices for MCP server development including proper error handling, health checks, multiple transport protocols (HTTP, SSE, streamable-HTTP), SSL support, and comprehensive development tooling.
Features
- FastMCP + FastAPI with multiple transport protocols (HTTP, SSE, streamable-HTTP)
- Three example tools: multiply calculator, code review prompt, Red Hat logo
- Pydantic configuration via environment variables
- Structured JSON logging with structlog
- SSL/TLS support for secure deployments
- Container-ready with Red Hat UBI base image
- OpenShift deployment manifests included
- Full CI/CD with GitHub Actions (tests, linting, security, releases)
- OAuth integration with PostgreSQL token storage
Quick Start
git clone https://github.com/redhat-data-and-ai/template-mcp-server
cd template-mcp-server
make install # creates venv, installs deps + pre-commit hooks
make local # starts server on localhost:5001
Verify in another terminal:
curl http://localhost:5001/health
<details> <summary>Manual setup (without Make)</summary>
# Create venv and install
uv venv && source .venv/bin/activate
uv pip install -e ".[dev]"
pre-commit install
# Configure and run
cp .env.example .env
template-mcp-server
# Verify
curl http://localhost:5001/health
</details>
How to Use This Template
Option 1: GitHub Template (Recommended)
- Click the "Use this template" button at the top of the repository page.
- Name your new repository (e.g.,
my-mcp-server). - Clone your new repository and follow the rename checklist below.
Option 2: Manual Clone
git clone https://github.com/redhat-data-and-ai/template-mcp-server.git my-mcp-server
cd my-mcp-server
rm -rf .git
git init
Rename Checklist
After creating your project, replace all references to template-mcp-server and template_mcp_server with your project name. The following files require updates:
| File / Directory | What to Change |
|---|---|
template_mcp_server/ |
Rename the package directory (e.g.,my_mcp_server/) |
pyproject.toml |
name, project.scripts entry, [project.urls], [tool.coverage.run] source |
Makefile |
References in lint, local, and deployment targets |
Containerfile |
COPY source path and CMD module path |
compose.yaml |
container_name, service name, healthcheck URL |
deployment/openshift/ |
App labels, image names, route hostnames in all manifests (deployment.yaml, route.yaml, kustomization.yaml, etc.) |
.github/workflows/ |
Workflow names and paths |
README.md |
Title, description, clone URL, and all badge URLs (tests, coverage, Codespaces) |
.env.example |
Adjust defaults if your server uses a different port or protocol |
Verify Rename
Run this to catch any leftover references:
grep -rn "template.mcp" --include="*.py" --include="*.yaml" --include="*.yml" --include="*.toml" --include="*.md" .
The output should be empty (or only match this README section itself).
Configuration
| Variable | Default | Description |
|---|---|---|
MCP_HOST |
localhost |
Server bind address |
MCP_PORT |
5001 |
Server port (1024-65535) |
MCP_TRANSPORT_PROTOCOL |
http |
Transport protocol (http, sse, streamable-http) |
MCP_SSL_KEYFILE |
None |
SSL private key file path |
MCP_SSL_CERTFILE |
None |
SSL certificate file path |
ENABLE_AUTH |
False* |
Enable OAuth authentication (see Auth Guide) |
USE_EXTERNAL_BROWSER_AUTH |
False |
Browser-based OAuth for local dev |
PYTHON_LOG_LEVEL |
INFO |
Logging level |
* ENABLE_AUTH defaults to False in .env.example but True in code. Always copy .env.example to .env to start with auth disabled.
Documentation
| Guide | Description |
|---|---|
| Architecture | System diagrams, code structure, key components, MCP tools |
| Development | Setup, running locally, testing, code quality |
| Deployment | Podman, OpenShift, container configuration |
| CI/CD | Workflows, pipeline features, running CI locally |
| Contributing | Development workflow, commit conventions, PR process |
| Security | Vulnerability reporting policy |
| Changelog | Release history |
| Authentication | OAuth setup, auth modes, troubleshooting |
| Tutorial | Your First Tool in 5 Minutes |
| Examples | FastMCP and LangGraph client examples |
Contributing
See CONTRIBUTING.md for detailed guidelines.
# Fork, clone, and set up
git clone https://github.com/<your-username>/template-mcp-server.git
cd template-mcp-server
make install
# Create a branch, make changes, verify
git checkout -b feat/your-feature
make lint && make test && make pre-commit
# Commit and open a PR
git commit -m "feat: your descriptive message"
git push origin feat/your-feature
License
推荐服务器
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。
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。
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。
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。
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。
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。
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。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
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。