Mimer

You can connect to a Mimer MCP Server to explore database schemas, run read-only queries with parameter support, and manage stored procedures. This server makes it easy to browse metadata, verify data safely, and invoke stored procedures from your MCP-enabled clients.

How to use

To use the Mimer MCP Server, connect with an MCP client using the provided HTTP endpoint or run the server locally and communicate via standard input/output. You can list available schemas, inspect tables, run read-only queries with parameter support, and explore or execute read-only stored procedures. Use the Tools exposed by the MCP to fetch metadata, execute queries, or run stored procedures as part of your data access workflows.

How to install

Prerequisites include Python 3.10 or later (with uv installed) or Docker, and Mimer SQL 11.0 or later.

Install and run via Docker (recommended for quick start):

# Build the local MCP server image (if you prefer to build locally)
docker build -t mimer-mcp-server .

# Run the MCP server using the official image
# Example: run the MCP server container directly
# This starts the MCP server and exposes its environment via the container
docker run -i --rm --add-host=host.docker.internal:host-gateway --env-file=/absolute/path/to/.env mimer-mcp-server

If you prefer to use Docker Compose to run both Mimer SQL and the MCP server, use a configuration that starts the Mimer SQL container and the MCP server in a private network, ensuring persistent data in a Docker volume named mimer_mcp_data.

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

Additional installation notes

Environment configuration is usually done through a .env file loaded at startup. The MCP server expects database connection details and logging preferences to control how it connects to the database and how loudly it logs activity.

Typical environment variables include the database DSN, user, password, host, and port, along with pool settings and the MCP log level. Ensure these values are set before starting the server.

Configuration and runtime notes

The server supports multiple ways to start, including Docker-based and uv-based runtimes. When using Docker, you can provide an environment file that contains your database credentials. When using uv, you can pass a path to the environment configuration via environment variables and start the server through the uv runtime.

If you need to test or debug MCP tooling interactively during development, you can use the MCP inspector with Node.js to explore endpoints and tool behavior. This helps you validate parameter binding and stored procedure handling before integrating into applications.

Security and best practices

Limit exposure of database credentials by using a dedicated environment file and restricting access to the host where the MCP server runs. Use least-privilege database credentials and enable health checks for pool connections to avoid stale or unhealthy connections from impacting queries.

Available 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

execute_query

Execute a SQL query with parameter support (read-only SELECT queries only)

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 with JSON parameters