Mimer MCP Server

A Model Context Protocol (MCP) server that provides Mimer SQL database connectivity to browse database schemas, execute read-only queries with parameterization support, and manage stored procedures.

<!-- mcp-name: io.github.mimersql/mimer-mcp -->

Available Tools

Database Schema Tools

• list_schemas — List all available schemas in the database
• list_table_names — List table names within the specified schema
• get_table_info — Get detailed table schema and sample rows

Query Execution Tools

• execute_query — Execute SQL query with parameter support (Only SELECT queries are allowed)

Stored Procedure Tools

• list_stored_procedures — List read-only stored procedures in the database
• get_stored_procedure_definition — Get the definition of a stored procedure
• get_stored_procedure_parameters — Get the parameters of a stored procedure
• execute_stored_procedure — Execute a stored procedure in the database with JSON parameters

Getting Started

Prerequisites

• Python 3.10 or later (with uv installed) _or_ Docker
• Mimer SQL 11.0 or later

Environment Configuration

Before running the server, you need to configure your database connection settings using environment variables. The Mimer MCP Server reads these from a .env file.

Mimer MCP Server can be configured using environment variables through .env file with the following configuration option:

Usage with VS Code

MCP servers are configured using a JSON file (mcp.json). Different MCP hosts may have slightly different configuration formats. In this guide, we'll focus on VS Code as an example. First, ensure you've installed the latest version of VS Code and have access to Copilot.

One way to add MCP server in VS Code is to add the server configuration to your workspace in the .vscode/mcp.json file. This will allow you to share configuration with others.

1. Create a .vscode/mcp.json file in your workspace.
2. Add the following configuration to your .vscode/mcp.json file, depending on how you want to run the MCP server.

Option 1: Using Docker (Recommended)

#### Option 1.1: Build the Docker Image Locally

docker build -t mimer-mcp-server .

Then, add the following configuration to .vscode/mcp.json file

{
	"servers": {
		"mimer-mcp-server": {
			"command": "docker",
			"args": [
				"run",
				"-i",
				"--rm",
				"--add-host=host.docker.internal:host-gateway",
				"--env-file=/absolute/path/to/.env",
				"mimer-mcp-server",
			]
		}
	},
	"inputs": []
}

#### Option 1.2: Use the Pre-Built Image from Docker Hub

{
    "servers": {
        "mimer-mcp-server": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "--add-host=host.docker.internal:host-gateway",
                "--env-file=/absolute/path/to/.env",
                "mimersql/mimer-mcp:latest"
            ]
        }
    },
    "inputs": []
}

Option 1.3: Use Docker compose and the official Mimer SQL docker container

This will start a Mimer SQL Docker container as well as the mimer-mcp-server container, set up a private network between the two containers and create the Mimer SQL example database. The Mimer SQL database will be stored in the docker volume called mimer_mcp_data so that database changes are persistent.

{
  "servers": {
    "mimer-mcp-server": {
      "command": "docker",
      "args": [
        "compose",
        "run",
        "--rm",
        "-i",
        "--no-TTY",
        "mimer-mcp-server"
      ]
    }
  },
  "inputs": []
}

Option 2: Using uv

{
	"servers": {
		"mimer-mcp-server": {
			"type": "stdio",
			"command": "uvx",
			"args": [
				"mimer_mcp_server"
			],
			"env": {
				"DOTENV_PATH": "/absolute/path/to/.env"
			}
		}
	}
}

1. After saving the configuration file, VS Code will display a Start button in the mcp.json file. Click it to launch the server.

<img src="docs/images/start-mcp-server.png" alt="Start button to start Mimer MCP Server" width=400>

1. Open Copilot Chat and in the Copilot Chat box, select Agent mode from the dropdown.

<img src="docs/images/copilot-agent-mode.png" alt="Copilot Chat Agent Mode" width=400>

1. Select the Tools button to view the list of available tools. Make sure the tools from Mimer MCP Server are selected.

<img src="docs/images/mimer-mcp-tools.png" alt="Tool Button on Chat" width=490%>

1. Enter a prompt in the chat input box and notice how the agent autonomously selects a suitable tool, fix errors and generate a final answer from gathered queries results. (Following examples use the Example Database from Mimer, which is owned by MIMER_STORE. Read more about this database: here)

<img src="docs/images/prompt-anthology.png" alt="Prompt asking what kind of product is Anthology" width=90%>

<img src="docs/images/agent-answer.png" alt="Agent answers with the gathered queries results" width=90%>

Development

Prerequisites

• Python: 3.10+
• uv: for dependency management and running the server
• Mimer SQL 11.0 or later
• Node.js and npm: for debugging with MCP inspector

#### Install uv:

# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# or via Homebrew
brew install uv

Verify installation:

uv --version

#### Install Node.js and npm:

# Linux (Ubuntu/Debian)
sudo apt install nodejs npm

# macOS (via Homebrew)
brew install node

Verify installation:

node --version
npm --version

Getting Started

1. Clone the repository

1. Create and activate a virtual environment

uv venv

# macOS / Linux
source .venv/bin/activate
# Windows
.venv\Scripts\activate

1. Install dependencies from pyproject.toml

uv sync

1. Configure environment variables

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

The configuration is loaded automatically via config.py.

Debug with MCP inspector

MCP Inspector provides a web interface for testing and debugging MCP Tools (Requires Node.js: 22.7.5+):

npx @modelcontextprotocol/inspector

Note: MCP Inspector is a Node.js app and the npx command allows running MCP Inspector without having to permanently install it as a Node.js package.

Alternatively, you can use FastMCP CLI to start the MCP inspector

uv run fastmcp dev /absolute/path/to/server.py

To run the Mimer SQL docker image and mimer-mcp-server using Docker compose, run:

MCP_TRANSPORT=http docker compose up

or to run it as a daemon:

MCP_TRANSPORT=http docker compose up -d

This way it is possible to call the mimer-mcp-server using HTTP and port 3333.