my-mcp-server
A FastMCP server that wraps a REST API as MCP tools, enabling AI agents to interact with the upstream API.
README
my-cmp-server
A FastMCP server that wraps a REST API as MCP tools.
Overview
This is a FastMCP server that exposes a REST API as a set of MCP (Model Context Protocol) tools. AI agents and LLMs can invoke these tools to interact with the upstream API.
Prerequisites
- Python 3.11+
- The upstream API running at
https://localhost:8080
Setup
python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt
### Run
```bash
python3 mcp_server.py
The server starts on http://0.0.0.0:8000/mcp using the
streamable HTTP transport.
Container Build
docker build -t my-cmp-server .
docker run -p 8000:8000 my-cmp-server
CI/CD with Pipelines as Code (Tekton)
This project uses Pipelines as Code (PAC) for fully automated CI/CD on
Openshift. No manual setup is required -- every push to main automatically
builds the container image and deploys to Openshift.
The pipeline definition lives in .tekton/push.yaml and performs:
- Clone -- fetches the repository source
- Build -- biulds the container image with buildah and pushes to the OpenShift internal registry
- Deploy -- applies the deployment manifests and rolls out the new version.
How it works
A GitHub webhook (created automatically by the RHDH template) sends push events
to the Pipelines as Code controller on Openshift. PAC reads .tekton/push.yaml
from the repo and creates a PipelineRun automatically.
Manual Deployment (without pipeline)
Apply the included manifests directly:
oc apply -f deploy/deployment.yaml
This creates a Deployment, Service, and Route in the mcp-servers
namespace. The Route provides a TLS-terminated public endpoint.
Customization
Edit mcp_server.py to replace the placeholder tools (list_items,
get_item,create_item) with tools that match your actual API endpoints.
Each @mcp.tool function maps to one REST endpoint:
| HTTP Method | MCP Tool Pattern |
|---|---|
| GET (list) | Tool that returns a list of resources |
| GET (by id) | Tool that returns a single resource |
| POST | Tool that creates a resource |
| PATCH / PUT | Tool that updates a resource |
| DELETE | Tool that removes a resource |
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。