Database

A server that helps people access and query data in databases using the Legion Query Runner with Model Context Protocol (MCP) in Python.

python

GitHub Stars

python

Language

6 months ago

First Indexed

2 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "theralabs-legion-mcp": {
      "command": "uvx",
      "args": [
        "database-mcp"
      ],
      "env": {
        "DB_TYPE": "pg",
        "DB_CONFIG": "{\"host\":\"localhost\",\"port\":5432,\"user\":\"user\",\"password\":\"pw\",\"dbname\":\"dbname\"}",
        "DB_CONFIGS": "[{\"id\":\"pg_main\",\"db_type\":\"pg\",\"configuration\":{...},\"description\":\"PostgreSQL Database\"}]"
      }
    }
  }
}

You can access and query multiple databases through a single MCP server that exposes database operations to AI assistants. This server uses the Model Context Protocol (MCP) SDK to present schemas, data, and query capabilities as MCP resources, tools, and prompts you can invoke from your AI workflow. It supports connecting to several database engines, handles credentials securely, and works with common AI development environments with minimal setup.

How to use

You use an MCP client to connect to the MCP server and perform operations like listing available databases, inspecting schemas, finding specific tables, and running SQL queries. For multi-database setups, you select the target database for each action using dedicated commands in your MCP client, and the server handles routing the request to the correct database.

How to install

Prerequisites: you need Python, and you may also use a Python MCP client or an MCP-compatible interface. You can run the server locally or through a package manager as shown.

Multi-database setup and usage notes

The server supports multiple databases at once. You specify a database identity for each operation so you target the right data source.

Security and deployment notes

Credential management is handled securely, with credentials separated from application code. When deploying, choose the environment and tooling you already use (for example, MCP-enabled FastAPI projects or other AI toolchains) and configure the database connections through environment variables or an MCP settings JSON.

Prompts and tools overview

You access database schemas, run queries, and retrieve results through MCP resources and tools such as listing databases, getting table schemas, describing tables, and executing SQL queries. These tools are designed to work uniformly across all connected databases.

Troubleshooting basics

If you encounter connection issues, verify your DB_TYPE and connection configuration, ensure your network allows access to the database endpoints, and check that the MCP server has the correct environment variables set for each database.

Available tools

execute_query

Execute a SQL query and return results as a markdown table

execute_query_json

Execute a SQL query and return results as JSON

get_table_columns

Get column names for a specific table

get_table_types

Get column types for a specific table

get_query_history

Get the recent query history

list_databases

List all available database connections

get_database_info

Get detailed information about a database including schema

find_table

Find which database contains a specific table

describe_table

Get detailed description of a table including column names and types

get_table_sample

Get a sample of data from a table

Built by

VeilStrat

AI signals for GTM teams