广告合作
MCP.so
登录

A Template MCP Server

@Alexander-Nestor-Bergmann

代码仓库

基本信息

分类

开发工具

许可证

MIT license

传输方式

stdio

作者

Alexander-Nestor-Bergmann

关于 A Template MCP Server

A template for how to build an MCP server

#docker#mcp#postgresql#mcp-server

A Template MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "agents-mcp-demo": {
      "command": "docker",
      "args": [
        "build",
        "-t",
        "sql-mcp-demo-server",
        "--build-arg",
        "PORT=${DB_PORT:-8051}",
        "."
      ]
    }
  }
}

A Template MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is A Template MCP Server?

A Template MCP Server is an example implementation of a Model Context Protocol (MCP) server that demonstrates how to connect AI agents and services (like Claude) to external data sources. It uses a PostgreSQL database backend to manage user data and exposes simple tools for user operations, serving as a reference for building MCP servers.

How to use A Template MCP Server?

Configure environment variables (especially DB_URL) in a .env file, then run the server using Docker or local Python. Connect an MCP client using either SSE (via Docker) or stdio transport (for local development). Example client configuration for SSE: set transport to sse and url to http://localhost:8051/sse.

Key features of A Template MCP Server

  • Defines and exposes custom tools via the MCP standard.
  • Handles requests from MCP clients and translates them into database operations.
  • Returns structured results or errors to the client.
  • Includes four example tools: add, list, find, and delete users.
  • Uses async PostgreSQL connection via SQLAlchemy with asyncpg driver.
  • Configurable via environment variables (e.g., DB_URL, DB_HOST, DB_PORT).

Use cases of A Template MCP Server

  • Learn how to build a basic MCP server with a database backend.
  • Prototype an AI agent that can query or modify user records.
  • Serve as a starting point for developing production MCP servers.

常见问题

1

What dependencies are required to run the server?

Requires Python 3.10+ and access to a PostgreSQL database. Docker is recommended for easy deployment; `uv` is used for local dependency management.

2

How do I configure the database connection?

Set the `DB_URL` environment variable to a PostgreSQL connection string using an asyncpg compatible prefix (e.g., `postgresql+asyncpg://user:pass@host:5432/dbname`). Additional optional variables like `DB_HOST`, `DB_PORT`, and `MCP_SIGNING_KEY` can be set in a `.env` file.

3

What transport options are available for connecting an MCP client?

The server supports both SSE (Server-Sent Events) transport, typically used when running via Docker, and stdio transport for local development. The client configuration must specify the transport type and appropriate connection details.

4

Is this server intended for production use?

No. The tools are simplified examples and the server is designed as a template to illustrate MCP server construction. The README explicitly states it is not for production use.

5

Where does the data live?

Data lives in a PostgreSQL database configured via the `DB_URL` environment variable. The server itself does not store data; it acts as a gateway to the external database.

评论

开发工具 分类下的更多 MCP 服务器

Apiosk

obcraft

AI-native payments for tools and APIs. Discover, pay for, execute, and publish monetized APIs directly from your agent, settled per call in USDC over x402, through the Model Context Protocol. payments · finance · x402 ·

SSH MCP Server

hypnosis

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

1

LocalCan

LocalCan

Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

82

DocBin

DocBin

Give an agent a place to put large output. Instead of returning 40k characters of a build log into the conversation, it posts the file to DocBin and hands back one short URL. Docs render with syntax highlighting and mark

Yocoolab

Yocoolab

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools

1
广告合作