Toolbox for Databases MCP server

Provides a secure, configurable interface for executing pre-defined queries against multiple database systems including PostgreSQL, MySQL, SQL Server, Neo4j, Dgraph, and Spanner through a YAML-based configuration system.
Back to servers
Setup instructions
Provider
Google
Release date
Apr 09, 2025
Language
Go
Stats
11.6K stars

The MCP Toolbox for Databases is an open source MCP server that simplifies the development of tools for database access. It handles complex tasks like connection pooling, authentication, and security, allowing you to focus on building powerful database tools for AI applications.

Installation

Binary Installation

Choose the appropriate method for your operating system:

Linux (AMD64)

# see releases page for other versions
export VERSION=0.21.0
curl -L -o toolbox https://storage.googleapis.com/genai-toolbox/v$VERSION/linux/amd64/toolbox
chmod +x toolbox

macOS (Apple Silicon)

# see releases page for other versions
export VERSION=0.21.0
curl -L -o toolbox https://storage.googleapis.com/genai-toolbox/v$VERSION/darwin/arm64/toolbox
chmod +x toolbox

macOS (Intel)

# see releases page for other versions
export VERSION=0.21.0
curl -L -o toolbox https://storage.googleapis.com/genai-toolbox/v$VERSION/darwin/amd64/toolbox
chmod +x toolbox

Windows (AMD64)

:: see releases page for other versions
set VERSION=0.21.0
curl -o toolbox.exe "https://storage.googleapis.com/genai-toolbox/v%VERSION%/windows/amd64/toolbox.exe"

Alternative Installation Methods

You can also install using:

  • Homebrew: brew install mcp-toolbox
  • Container image: docker pull us-central1-docker.pkg.dev/database-toolbox/toolbox/toolbox:$VERSION
  • Compile from source: go install github.com/googleapis/[email protected]

Running the Server

  1. Create a tools.yaml configuration file (see Configuration section)
  2. Start the server with:
./toolbox --tools-file "tools.yaml"

To stop the server, press ctrl+c.

Integrating with Your Application

Python SDK

from toolbox_core import ToolboxClient

# update the url to point to your server
async with ToolboxClient("http://127.0.0.1:5000") as client:
    # these tools can be passed to your application!
    tools = await client.load_toolset("toolset_name")

JavaScript/TypeScript SDK

import { ToolboxClient } from '@toolbox-sdk/core';

// update the url to point to your server
const URL = 'http://127.0.0.1:5000';
let client = new ToolboxClient(URL);

// these tools can be passed to your application!
const tools = await client.loadToolset('toolsetName');

Go SDK

package main

import (
  "github.com/googleapis/mcp-toolbox-sdk-go/tbadk"
  "context"
  "fmt"
)

func main() {
  // Update the url to point to your server
  URL := "http://127.0.0.1:5000"
  ctx := context.Background()
  client, err := tbadk.NewToolboxClient(URL)
  if err != nil {
    fmt.Println("Could not start Toolbox Client", err)
    return
  }

  // Use this tool with ADK Go
  tool, err := client.LoadTool("toolName", ctx)
  if err != nil {
    fmt.Println("Could not load Toolbox Tool", err)
    return
  }
}

Configuration

The primary way to configure Toolbox is through the tools.yaml file.

Sources

Define database connections:

sources:
  my-pg-source:
    kind: postgres
    host: 127.0.0.1
    port: 5432
    database: toolbox_db
    user: toolbox_user
    password: my-password

Tools

Define the actions an agent can perform:

tools:
  search-hotels-by-name:
    kind: postgres-sql
    source: my-pg-source
    description: Search for hotels based on name.
    parameters:
      - name: name
        type: string
        description: The name of the hotel.
    statement: SELECT * FROM hotels WHERE name ILIKE '%' || $1 || '%';

Toolsets

Group tools together for easier loading:

toolsets:
    my_first_toolset:
        - my_first_tool
        - my_second_tool
    my_second_toolset:
        - my_second_tool
        - my_third_tool

Prompts

Define prompts for interactions with LLMs:

prompts:
  code_review:
    description: "Asks the LLM to analyze code quality and suggest improvements."
    messages:
      - content: "Please review the following code for quality, correctness, and potential improvements: \n\n{{.code}}"
    arguments:
      - name: "code"
        description: "The code to review"

Using with Gemini CLI Extensions

To use custom tools with Gemini CLI:

gemini extensions install https://github.com/gemini-cli-extensions/mcp-toolbox

Several prebuilt extensions exist for specific database types, including AlloyDB, BigQuery, Cloud SQL, MySQL, PostgreSQL, Spanner, and more. Each of these can be installed via Gemini CLI extensions.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "toolbox-for-databases" '{"command":"toolbox","args":["--tools-file","tools.yaml"]}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "toolbox-for-databases": {
            "command": "toolbox",
            "args": [
                "--tools-file",
                "tools.yaml"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "toolbox-for-databases": {
            "command": "toolbox",
            "args": [
                "--tools-file",
                "tools.yaml"
            ]
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later