trackmcp
Back to directory
Shion-Serizawa

mcp-first

View on GitHub
0 stars PythonOthers Updated Oct 5, 2025

Documentation

MySQL Schema MCP Server

A Metadata Change Proposal (MCP) server for retrieving MySQL database schema information using the FastMCP framework.

Features

  • Retrieve database list
  • Retrieve table list from databases
  • Get table schema (columns) information
  • Get table indexes information
  • Get table foreign key information

Setup

Local Setup with uv

1. Clone this repository

2. Install uv if you don't have it already:

bash
pip install uv

3. Create a virtual environment and install dependencies:

bash
uv venv
   uv pip install -r requirements.txt

4. Create a `.env` file based on `.env.example` with your MySQL connection details:

code
MYSQL_HOST=localhost
   MYSQL_PORT=3306
   MYSQL_USER=your_username
   MYSQL_PASSWORD=your_password
   MYSQL_DATABASE=information_schema

Local Setup with pip

1. Clone this repository

2. Install dependencies:

code
pip install -r requirements.txt

3. Create a `.env` file based on `.env.example` with your MySQL connection details:

code
MYSQL_HOST=localhost
   MYSQL_PORT=3306
   MYSQL_USER=your_username
   MYSQL_PASSWORD=your_password
   MYSQL_DATABASE=information_schema

Docker Setup

Building and Running the Docker Image

1. Clone this repository

2. Build the Docker image:

code
docker build -t mysql-mcp-server .

3. Run the Docker container with environment variables for MySQL connection:

code
docker run -p 8000:8000 \
     -e MYSQL_HOST=host.docker.internal \
     -e MYSQL_PORT=3306 \
     -e MYSQL_USER=your_username \
     -e MYSQL_PASSWORD=your_password \
     -e MYSQL_DATABASE=information_schema \
     mysql-mcp-server

Note: `host.docker.internal` is used to connect to the MySQL instance running on your host machine from inside the Docker container.

4. For Mac and Windows, `host.docker.internal` resolves to the host machine. For Linux, you may need to use:

code
docker run -p 8000:8000 \
     --add-host=host.docker.internal:host-gateway \
     -e MYSQL_HOST=host.docker.internal \
     -e MYSQL_USER=your_username \
     -e MYSQL_PASSWORD=your_password \
     mysql-mcp-server

Usage

Local Usage

Start the server:

code
python main.py

Docker Usage

Run the Docker container (as shown in the setup section):

code
docker run -p 8000:8000 \
  -e MYSQL_HOST=host.docker.internal \
  -e MYSQL_USER=your_username \
  -e MYSQL_PASSWORD=your_password \
  mysql-mcp-server

You can also create a `.env` file and mount it to the container:

code
docker run -p 8000:8000 \
  -v $(pwd)/.env:/app/.env \
  mysql-mcp-server

MCP JSON Configuration

To use this MCP server with MCP-compatible clients, you'll need to configure the client with the appropriate JSON configuration. Here are examples for both local and Docker setups:

Local MCP Configuration

json
{
  "mcpServers": {
    "mysql-schema": {
      "command": "python",
      "args": [
        "main.py"
      ],
      "cwd": "/path/to/mcp-first",
      "alwaysAllow": [
        "databases",
        "tables",
        "schema",
        "indexes",
        "foreign_keys"
      ]
    }
  }
}

Docker MCP Configuration

json
{
  "mcpServers": {
    "mysql-schema": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "MYSQL_HOST=host.docker.internal",
        "-e",
        "MYSQL_USER=your_username",
        "-e",
        "MYSQL_PASSWORD=your_password",
        "mysql-mcp-server"
      ],
      "alwaysAllow": [
        "databases",
        "tables",
        "schema",
        "indexes",
        "foreign_keys"
      ]
    }
  }
}

Available Tools

The server provides the following tools:

  • `databases`: List all databases
  • `tables`: List all tables in a database
  • `schema`: Get the schema (columns, indexes, and foreign keys) for one or more tables.
  • `indexes`: Get the indexes for a specific table
  • `foreign_keys`: Get the foreign keys for a specific table

Example

python
from fastmcp.client import Client

# Connect to the MCP server
client = Client("http://localhost:8000")

# List all databases
databases = client.databases()

# List tables in a specific database
tables = client.tables(database="your_database")

# Get schema for a specific table
schema = client.schema(tables=["your_table"], database="your_database")

# Get schema for multiple tables
schemas = client.schema(tables=["table1", "table2"], database="your_database")

# Get indexes for a specific table
indexes = client.indexes(table="your_table", database="your_database")

# Get foreign keys for a specific table
foreign_keys = client.foreign_keys(table="your_table", database="your_database")

Frequently asked questions

What is mcp-first?

mcp-first is a Model Context Protocol (MCP) server listed in the TrackMCP directory.

How do I install mcp-first?

Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.

Is mcp-first open source?

Yes — it is hosted on GitHub at https://github.com/Shion-Serizawa/mcp-first.

Related MCP tools

mem0aimem0-mcp

5. Update .env file in the root directory with your mem0 API key: for the Model Context Protocol. Enhance AI assistants with powerful integrations.

499 Python
24mlighta-share-mcp-is-just-i-need

Model Context Protocol integration for Python. Enhance AI assistants with powerful Python-based capabilities and integration support.

440 Python
googlemcp-security

This repository contains Model Context Protocol (MCP) servers that enable MCP clients (like Claude Desktop or the cline.

394 Python
All-Hands-AIopenhands

🙌 OpenHands: Code Less, Make More for the Model Context Protocol. Enhance AI assistants with powerful integrations. Python-based implementation.

64,677 Python
agentartificial-intelligencechatgpt+6
mem0aimem0

Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management. Python-based implementation.

42,646 Python
agentsaiai-agents+12
zhayujiechatgpt-on-wechat

基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择ChatGPT/Claude/DeepSeek/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。

39,573 Python
aiai-agentchatgpt+17

Run your own MCP server? See who uses it and what to fix.

Measure it with TrackMCP