Server profile

MCP Toolbox for Databases

MCP Toolbox for Databases connects agents and IDEs to enterprise data through prebuilt tools or custom query definitions. It combines database access with connection pooling, authentication integration, and observability.

Server facts

MCP Toolbox for Databases

Tech

Runtime / language
goGo
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
16,669
Last commit
Data as of

Tags

  • Connection Pooling
  • Custom Tools
  • Databases
  • Opentelemetry
  • Sql

Overview

MCP Toolbox for Databases serves two related purposes. Developers can connect an MCP client to a database using prebuilt generic tools for exploration and SQL work, or define narrower custom tools for production agents. The README names table listing and SQL execution as examples of the prebuilt interface. Custom definitions describe sources, parameters, statements, and toolsets in a tools.yaml configuration file, allowing teams to expose deliberate operations rather than only a generic database connection. Supported systems span Google Cloud databases and other platforms, including PostgreSQL, MySQL, MongoDB, Redis, Neo4j, Snowflake, and additional engines.

The server handles connection pooling, integrated authentication including IAM, and observability through OpenTelemetry. An npm launch example configures prebuilt PostgreSQL tools over stdio, while custom configurations can also run through npm, a downloaded binary, a container, Homebrew installation, or source execution. Connection environment variables depend on the chosen prebuilt database and are referred to separate reference documentation rather than enumerated in this README. The project recommends binaries or containers for a more standard and reliable installation than the convenience-oriented npm route. It also clarifies that the repository was renamed from genai-toolbox to mcp-toolbox. For teams building database-aware assistants, the distinction between exploratory tools and restricted custom queries is the main architectural choice offered by this project.

Install & configure

Requirements

  • An MCP-compatible client
  • npx for this execution method
  • A PostgreSQL database for this example
  • Database-specific connection settings from the prebuilt reference
Documented launch / install command
npx -y @toolbox-sdk/server --prebuilt=postgres --stdio

This is the README's prebuilt PostgreSQL example. Exact database connection environment variables are not stated in the supplied README, so none are invented here. Binaries and containers are recommended for a more standard installation. The repository is now named mcp-toolbox.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "genai-toolbox": {
      "command": "npx",
      "args": [
        "-y",
        "@toolbox-sdk/server",
        "--prebuilt=postgres",
        "--stdio"
      ],
      "env": {}
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "genai-toolbox": {
      "command": "npx",
      "args": [
        "-y",
        "@toolbox-sdk/server",
        "--prebuilt=postgres",
        "--stdio"
      ],
      "env": {}
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "genai-toolbox": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@toolbox-sdk/server",
        "--prebuilt=postgres",
        "--stdio"
      ],
      "env": {}
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "genai-toolbox": {
      "command": "npx",
      "args": [
        "-y",
        "@toolbox-sdk/server",
        "--prebuilt=postgres",
        "--stdio"
      ],
      "env": {}
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "genai-toolbox": {
      "type": "stdio",
      "command": "npx",
      "args": [
        "-y",
        "@toolbox-sdk/server",
        "--prebuilt=postgres",
        "--stdio"
      ],
      "env": {}
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

Source: repository README. Tool descriptions are a documented snapshot, not a live capability check.

ToolWhat it does
list_tablesDiscover database tables through a prebuilt generic tool.
execute_sqlExecute SQL through the database's prebuilt tool interface.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Explore database schemas from a coding assistant.
  • Run database queries through prebuilt MCP tools.
  • Define parameterized custom operations for production agents.
  • Group database tools into task-specific toolsets.
  • Observe database-tool activity with metrics and tracing.

Strengths

  • Supports both prebuilt exploration and custom query tools.
  • Covers numerous cloud and non-cloud database engines.
  • Includes connection pooling, integrated authentication, and OpenTelemetry support.

Limitations

  • Connection configuration is database-specific and requires separate reference details.
  • The README characterizes npm execution as convenience-oriented rather than the most reliable installation.
  • Custom tools require source and query definitions.

Frequently asked questions

No. The README also lists systems such as PostgreSQL, MySQL, Oracle, MongoDB, Redis, Neo4j, and Snowflake.

Prebuilt tools provide generic access, while custom tools define source connections, parameters, and operations in configuration such as tools.yaml.

Yes. Toolsets group selected tools so they can be loaded together for particular applications or agents.

The README explains that genai-toolbox was renamed to mcp-toolbox, while the product is called MCP Toolbox for Databases.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

Neon MCP Server

Databases

Manage Neon Postgres projects, branches, queries, and migrations through an AI assistant. The hosted MCP service supports OAuth or API keys, read-only access, and project-level scoping.

MCP Server for MySQL

Databases

MCP Server for MySQL lets Claude and other AI clients inspect schemas and execute SQL. It defaults to read-only access, with optional write flags, SSH tunneling, multi-database support, and result redaction.

DBHub

Databases

DBHub exposes SQL execution and database discovery through a small MCP interface. It spans five database engines, supports multiple configured connections, and includes a web workbench for use without an assistant.

Supabase MCP Server

Databases

Connect AI assistants to Supabase projects for SQL, schema changes, debugging, and Edge Functions. Hosted HTTP setup supports project scoping, read-only access, and selectable feature groups.

Postgres MCP Pro

Databases

Give assistants PostgreSQL schema access, SQL execution, health checks, and performance analysis. Postgres MCP Pro adds query plans and hypothetical index evaluation with configurable read-only operation.

MySQL MCP Server

Databases

Expose MySQL schema inspection, data samples, and SQL execution to MCP assistants. It supports multi-database access, optional SSH tunnels, and local or network deployment, with database permissions controlling available operations.

MongoDB MCP Server

Databases

MongoDB MCP Server connects AI clients to MongoDB databases and Atlas. Its tools cover queries, schema inspection, database changes, and MongoDB knowledge searches, with read-only launch examples for safer exploration.

Query MCP for Supabase

Databases

Query MCP connects coding assistants to Supabase SQL, schema changes, project management, and user administration. It includes SQL risk controls, but its author has stopped active maintenance.