Building a Simple MCP Server in Python Using the MCP Python SDK
@ruslanmv
Building a Simple MCP Server in Python Using the MCP Python SDK について
The Model Context Protocol (MCP) is a standardized way to supply context to large language models (LLMs). Using the MCP Python SDK, you can build servers that expose data (resources), functionality (tools), and interaction templates (prompts) to LLM applications in a secure and m
基本情報
設定
以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。
{
"mcpServers": {
"Simple-MCP-Server-with-Python": {
"command": "uv",
"args": [
"init",
"mcp-server"
]
}
}
}ツール
ツールは検出されませんでした
ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。
概要
What is Building a Simple MCP Server in Python Using the MCP Python SDK?
This is a step‑by‑step tutorial for creating a Model Context Protocol (MCP) server in Python using the official MCP Python SDK. It teaches how to expose resources (data), tools (functions), and prompts (templates) that LLM applications can consume in a secure, modular way.
How to use Building a Simple MCP Server in Python Using the MCP Python SDK?
First, ensure Python 3.7+ (preferably 3.11+), pip, and Node.js 18.x are installed. Install the MCP Python SDK with pip install "mcp[cli]" or via uv add "mcp[cli]". Create a project directory with a server.py file, define tools using @mcp.tool(), resources with @mcp.resource(), and optional prompts with @mcp.prompt(). Run the server with mcp dev server.py to open the MCP Inspector at http://localhost:6274/.
Key features of Building a Simple MCP Server in Python Using the MCP Python SDK?
- Uses
FastMCPfrom the MCP Python SDK for easy server creation. - Exposes a calculator tool (
add) that accepts two integers. - Provides a dynamic greeting resource at
greeting://{name}. - Supports an optional
review_codeprompt template. - Includes live reloading during development via
mcp dev.
Use cases of Building a Simple MCP Server in Python Using the MCP Python SDK?
- Supply an addition tool that LLM applications can call to perform calculations.
- Serve personalized greeting data to enrich LLM context.
- Offer reusable code‑review prompts for interactive LLM workflows.
- Demonstrate the three MCP primitives (resources, tools, prompts) in a single server.
FAQ from Building a Simple MCP Server in Python Using the MCP Python SDK?
What is MCP?
The Model Context Protocol (MCP) standardizes the interface between applications and LLMs, separating concerns of providing context, executing code, and managing user interactions.
What are the prerequisites to build and run the server?
Python 3.7+ (preferably 3.11+), pip, Node.js 18.x, and the MCP Python SDK installed via pip install "mcp[cli]" or uv add "mcp[cli]".
How do I run the server and test it?
Activate your virtual environment, then run mcp dev server.py in your project directory. This starts the server using the default STDIO transport and launches the MCP Inspector web UI.
What primitives can an MCP server expose?
Prompts (user‑controlled), resources (application‑controlled), and tools (model‑controlled). The tutorial implements all three.
What transport does the server use by default?
The server uses the STDIO transport when started with mcp dev.
「開発者ツール」の他のコンテンツ
MCP Framework
QuantGeekDevThe Typescript MCP Framework
OpenSumi
opensumiA framework helps you quickly build AI Native IDE products. MCP Client, supports Model Context Protocol (MCP) tools via MCP server.
sentry-mcp
getsentryAn MCP server for interacting with Sentry via LLMs.
MCP Containers
metorialConnect any AI model to 1200+ integrations (MCP, CLI, API)
test
cloudwegoThe ultimate LLM/AI application development framework in Go.
コメント