Skip to main content
Glama

database-mcp

Multi-Database MCP Server (by Legion AI)

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

Start Generation Here

This tool is provided by Legion AI. To use the full-fledged and fully powered AI data analytics tool, please visit the site. Email us if there is one database you want us to support.

End Generation Here

Why Choose Database MCP

Database MCP stands out from other database access solutions for several compelling reasons:

  • Unified Multi-Database Interface: Connect to PostgreSQL, MySQL, SQL Server, and other databases through a single consistent API - no need to learn different client libraries for each database type.
  • AI-Ready Integration: Built specifically for AI assistant interactions through the Model Context Protocol (MCP), enabling natural language database operations.
  • Zero-Configuration Schema Discovery: Automatically discovers and exposes database schemas without manual configuration or mapping.
  • Database-Agnostic Tools: Find tables, explore schemas, and execute queries with the same set of tools regardless of the underlying database technology.
  • Secure Credential Management: Handles database authentication details securely, separating credentials from application code.
  • Simple Deployment: Works with modern AI development environments like LangChain, FastAPI, and others with minimal setup.
  • Extensible Design: Easily add custom tools and prompts to enhance functionality for specific use cases.

Whether you're building AI agents that need database access or simply want a unified interface to multiple databases, Database MCP provides a streamlined solution that dramatically reduces development time and complexity.

Features

  • Multi-database support - connect to multiple databases simultaneously
  • Database access via Legion Query Runner
  • Model Context Protocol (MCP) support for AI assistants
  • Expose database operations as MCP resources, tools, and prompts
  • Multiple deployment options (standalone MCP server, FastAPI integration)
  • Query execution and result handling
  • Flexible configuration via environment variables, command-line arguments, or MCP settings JSON
  • User-driven database selection for multi-database setups

Supported Databases

DatabaseDB_TYPE code
PostgreSQLpg
Redshiftredshift
CockroachDBcockroach
MySQLmysql
RDS MySQLrds_mysql
Microsoft SQL Servermssql
Big Querybigquery
Oracle DBoracle
SQLitesqlite

We use Legion Query Runner library as connectors. You can find more info on their api doc.

What is MCP?

The Model Context Protocol (MCP) is a specification for maintaining context in AI applications. This server uses the MCP Python SDK to:

  • Expose database operations as tools for AI assistants
  • Provide database schemas and metadata as resources
  • Generate useful prompts for database operations
  • Enable stateful interactions with databases

Installation & Configuration

Required Parameters

For single database configuration:

  • DB_TYPE: The database type code (see table above)
  • DB_CONFIG: A JSON configuration string for database connection

For multi-database configuration:

  • DB_CONFIGS: A JSON array of database configurations, each containing:
    • db_type: The database type code
    • configuration: Database connection configuration
    • description: A human-readable description of the database

The configuration format varies by database type. See the API documentation for database-specific configuration details.

Installation Methods

When using uv, no specific installation is needed. We will use uvx to directly run database-mcp.

UV Configuration Example (Single Database):

REPLACE DB_TYPE and DB_CONFIG with your connection info. { "mcpServers": { "database-mcp": { "command": "uvx", "args": [ "database-mcp" ], "env": { "DB_TYPE": "pg", "DB_CONFIG": "{\"host\":\"localhost\",\"port\":5432,\"user\":\"user\",\"password\":\"pw\",\"dbname\":\"dbname\"}" }, "disabled": true, "autoApprove": [] } } }

UV Configuration Example (Multiple Databases):

{ "mcpServers": { "database-mcp": { "command": "uvx", "args": [ "database-mcp" ], "env": { "DB_CONFIGS": "[{\"id\":\"pg_main\",\"db_type\":\"pg\",\"configuration\":{\"host\":\"localhost\",\"port\":5432,\"user\":\"user\",\"password\":\"pw\",\"dbname\":\"postgres\"},\"description\":\"PostgreSQL Database\"},{\"id\":\"mysql_data\",\"db_type\":\"mysql\",\"configuration\":{\"host\":\"localhost\",\"port\":3306,\"user\":\"root\",\"password\":\"pass\",\"database\":\"mysql\"},\"description\":\"MySQL Database\"}]" }, "disabled": true, "autoApprove": [] } } }
Option 2: Using PIP

Install via pip:

pip install database-mcp

PIP Configuration Example (Single Database):

{ "mcpServers": { "database": { "command": "python", "args": [ "-m", "database_mcp", "--repository", "path/to/git/repo" ], "env": { "DB_TYPE": "pg", "DB_CONFIG": "{\"host\":\"localhost\",\"port\":5432,\"user\":\"user\",\"password\":\"pw\",\"dbname\":\"dbname\"}" } } } }

Running the Server

Production Mode

python mcp_server.py

Configuration Methods

Environment Variables (Single Database)
export DB_TYPE="pg" # or mysql, postgresql, etc. export DB_CONFIG='{"host":"localhost","port":5432,"user":"username","password":"password","dbname":"database_name"}' uv run src/database_mcp/mcp_server.py
Environment Variables (Multiple Databases)
export DB_CONFIGS='[{"id":"pg_main","db_type":"pg","configuration":{"host":"localhost","port":5432,"user":"username","password":"password","dbname":"database_name"},"description":"PostgreSQL Database"},{"id":"mysql_users","db_type":"mysql","configuration":{"host":"localhost","port":3306,"user":"root","password":"pass","database":"mysql"},"description":"MySQL Database"}]' uv run src/database_mcp/mcp_server.py

If you don't specify an ID, the system will generate one automatically based on the database type and description:

export DB_CONFIGS='[{"db_type":"pg","configuration":{"host":"localhost","port":5432,"user":"username","password":"password","dbname":"database_name"},"description":"PostgreSQL Database"},{"db_type":"mysql","configuration":{"host":"localhost","port":3306,"user":"root","password":"pass","database":"mysql"},"description":"MySQL Database"}]' # IDs will be generated as something like "pg_postgres_0" and "my_mysqldb_1" uv run src/database_mcp/mcp_server.py
Command Line Arguments (Single Database)
python mcp_server.py --db-type pg --db-config '{"host":"localhost","port":5432,"user":"username","password":"password","dbname":"database_name"}'
Command Line Arguments (Multiple Databases)
python mcp_server.py --db-configs '[{"id":"pg_main","db_type":"pg","configuration":{"host":"localhost","port":5432,"user":"username","password":"password","dbname":"database_name"},"description":"PostgreSQL Database"},{"id":"mysql_users","db_type":"mysql","configuration":{"host":"localhost","port":3306,"user":"root","password":"pass","database":"mysql"},"description":"MySQL Database"}]'

Note that you can specify custom IDs for each database using the id field, or let the system generate them based on database type and description.

Multi-Database Support

When connecting to multiple databases, you need to specify which database to use for each query:

  1. Use the list_databases tool to see available databases with their IDs
  2. Use get_database_info to view schema details of databases
  3. Use find_table to locate a table across all databases
  4. Provide the db_id parameter to tools like execute_query, get_table_columns, etc.

Database connections are managed internally as a dictionary of DbConfig objects, with each database having a unique ID. Schema information is represented as a list of table objects, where each table contains its name and column information.

The select_database prompt guides users through the database selection process.

Schema Representation

Database schemas are represented as a list of table objects, with each table containing information about its columns:

[ { "name": "users", "columns": [ {"name": "id", "type": "integer"}, {"name": "username", "type": "varchar"}, {"name": "email", "type": "varchar"} ] }, { "name": "orders", "columns": [ {"name": "id", "type": "integer"}, {"name": "user_id", "type": "integer"}, {"name": "product_id", "type": "integer"}, {"name": "quantity", "type": "integer"} ] } ]

This representation makes it easy to programmatically access table and column information while keeping a clean hierarchical structure.

Exposed MCP Capabilities

Resources

ResourceDescription
resource://schema/{database_id}Get the schemas for one or all configured databases

Tools

ToolDescription
execute_queryExecute a SQL query and return results as a markdown table
execute_query_jsonExecute a SQL query and return results as JSON
get_table_columnsGet column names for a specific table
get_table_typesGet column types for a specific table
get_query_historyGet the recent query history
list_databasesList all available database connections
get_database_infoGet detailed information about a database including schema
find_tableFind which database contains a specific table
describe_tableGet detailed description of a table including column names and types
get_table_sampleGet a sample of data from a table

All database-specific tools (like execute_query, get_table_columns, etc.) require a db_id parameter to specify which database to use.

Prompts

PromptDescription
sql_queryCreate an SQL query against the database
explain_queryExplain what a SQL query does
optimize_queryOptimize a SQL query for better performance
select_databaseHelp user select which database to use

Development

Using MCP Inspector

run this to start the inspector

npx @modelcontextprotocol/inspector uv run src/database_mcp/mcp_server.py

then in the command input field, set something like

run src/database_mcp/mcp_server.py --db-type pg --db-config '{"host":"localhost","port":5432,"user":"username","password":"password","dbname":"database_name"}'

Testing

uv pip install -e ".[dev]" pytest

Publishing

# Clean up build artifacts rm -rf dist/ build/ # Remove any .egg-info directories if they exist find . -name "*.egg-info" -type d -exec rm -rf {} + 2>/dev/null || true # Build the package uv run python -m build # Upload to PyPI uv run python -m twine upload dist/*

License

This repository is licensed under GPL

-
security - not tested
A
license - permissive license
-
quality - not tested

hybrid server

The server is able to function both locally and remotely, depending on the configuration or use case.

A server that helps people access and query data in databases using the Query Runner with integration of the Model Context Protocol (MCP) Python SDK. Supported by Legion AI team (thelegionai.com)

Support databases including PostgreSQL Redshift MySQL Microsoft SQL Server Google APIs Amazon Web Services (via boto3) CockroachDB SQLite

  1. Start Generation Here
    1. End Generation Here
      1. Why Choose Database MCP
      2. Features
      3. Supported Databases
      4. What is MCP?
      5. Installation & Configuration
      6. Running the Server
      7. Multi-Database Support
      8. Schema Representation
      9. Exposed MCP Capabilities
      10. Development
      11. License

    Related MCP Servers

    • -
      security
      F
      license
      -
      quality
      A server that enables interaction with PostgreSQL, MySQL, MariaDB, or SQLite databases through Claude Desktop using natural language queries.
      Last updated -
      Python
    • -
      security
      A
      license
      -
      quality
      This is a Model Context Protocol (MCP) server for executing SQL queries against Databricks using the Statement Execution API. It enables AI assistants to directly query Databricks data warehouses, analyze database schemas, and retrieve query results in a structured format
      Last updated -
      8
      Python
      MIT License
      • Linux
      • Apple
    • -
      security
      A
      license
      -
      quality
      A Model Context Protocol server that provides Claude access to Turso-hosted LibSQL databases, enabling database table listing, schema retrieval, and SELECT query execution.
      Last updated -
      68
      5
      TypeScript
      MIT License
      • Apple
    • -
      security
      A
      license
      -
      quality
      An MCP server that enables MySQL database integration with Claude. You can execute SQL queries and manage database connections.
      Last updated -
      1
      Python
      MIT License
      • Apple

    View all related MCP servers

    MCP directory API

    We provide all the information about MCP servers via our MCP API.

    curl -X GET 'https://glama.ai/api/mcp/v1/servers/TheRaLabs/legion-mcp'

    If you have feedback or need assistance with the MCP directory API, please join our Discord server