Skeleton

Simple template that a MCP server can be based on

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "nickweedon-mcp_server_template": {
      "command": "uv",
      "args": [
        "run",
        "skeleton-mcp"
      ],
      "env": {
        "ENV": "YOUR_ENV_VALUE"
      }
    }
  }
}

You are setting up a reusable MCP server to expose your data and actions through the Model Context Protocol. This skeleton provides a solid, tested foundation with FastMCP, Docker support, and example CRUD APIs to help you build, run, and iterate quickly.

How to use

Run your MCP server locally or in a container, then connect an MCP client to perform create, read, update, and delete operations against example endpoints. You can extend the example API to match your own data model and tools. Docker or Dev Containers simplify running in consistent environments, and tests help verify behavior as you evolve.

How to install

Prerequisites: Python 3.10 or higher, uv package manager (recommended), and Docker if you want containerized deployment.

Clone the project and rename it for your work:

git clone <this-repo> my-mcp-server
cd my-mcp-server

Rename the package to match your project name and update metadata:

# Rename the package directory
# From: src/skeleton_mcp/
# To:   src/your_project_name/

# Update pyproject.toml with your project name and metadata
# Update imports in all Python files

Install dependencies using the uv workflow:

uv sync

Create your environment file from the example and edit credentials:

cp .env.example .env
# Edit .env with your API credentials

Start the server locally using uv:

uv run skeleton-mcp

Additional setup and deployment

If you prefer containerized deployment, you can use Docker Compose to build and run the MCP server in containers.

docker compose up --build

For development with VS Code, you can use the Dev Container configuration to open and work inside a consistent containerized environment.

Notes on project structure and development

The skeleton demonstrates a complete layout with an API module for example CRUD operations, a test suite, utilities, and Claude Code integration. It includes tooling to test, lint, and build, plus a ready-to-extend API surface you can adapt to your data model.

Claude Desktop and tooling integration

You can invoke MCP actions from Claude Desktop by configuring a server entry that runs or communicates with the MCP server in your environment. This enables convenient, scriptable interactions with your backend while developing.

Available tools

health_check

Check server health and configuration status

list_items

List all items with filtering and pagination

get_item

Get a specific item by ID

create_item

Create a new item

update_item

Update an existing item

delete_item

Delete an item