About Mcp Server
Mcp Server is a project centered on building and running MCP servers with Docker, with image examples for YouTube, weather, and a knowledge graph. It is for developers managing containerized MCP services.
Key features
- 01Build Docker images for MCP servers
- 02Run containerized MCP servers
- 03Inspect running containers
- 04Stop containers by ID or name
Use cases
- 01Build a Docker image for the weather service
- 02Run and manage containerized MCP servers
MCP support
The project is for building and running MCP servers. The README mentions tools, resources, and prompts but does not specify what each service exposes.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEquick start
uv init --python 3.13 // 원하는 버전
uv venv // .venv 가상환경 설치
// Window
./.venv/Scripts/activate
// MacOS
source .venv/bin/activate
// 라이브러리 설치
uv pip install -e .
docker
//docker build
docker image build -t (도커이미지이름) -f (폴더명)/Dockerfile .
docker image build -t mcp/youtube -f youtube/Dockerfile .
docker image build -t mcp/weather -f weather/Dockerfile .
docker image build -t mcp/knowledge_graph -f memgraph/Dockerfile .
// docker execution(mcp서버가 알아서 실행하기때문에 안해도됨)
docker run -p 8006:8006 -i --rm mcp/weather
//docker container stop
docker ps //빌드된 컨테이너 목록
docker stop (container ID or name)
//docker image delete
docker images // 빌드된 이미지 목록
docker rmi (REPOSITORY)
exit docker container
// 실행중인 컨테이너 확인
docker ps
// 출력
CONTAINER ID IMAGE COMMAND CREATED STATUS PORTS NAMES
6784f3bbb400 5db99b68d643 "uv run mcp run tool…" 9 minutes ago Up 9 minutes 0.0.0.0:8006->8006/tcp zen_liskov
// container id를 이용하거나 이름으로 중지
docker stop 6784f3bbb400
docker stop zen_liskov
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.