MCP Toolbox for Databases is an open source Model Context Protocol (MCP) server that connects your AI agents, IDEs, and applications directly to your enterprise databases.
How to install mcp-toolbox?
googleapis/mcp-toolbox
$git clone https://github.com/googleapis/mcp-toolboxInstalls into the current project.
›Prefer a prompt? Paste this to your agent
Install mcp-toolbox by running `git clone https://github.com/googleapis/mcp-toolbox`, then use it for the current task and follow its documentation at https://github.com/googleapis/mcp-toolbox.
README.md
| 1 | <div align="center"> |
| 2 | |
| 3 |  |
| 4 | |
| 5 | # MCP Toolbox for Databases |
| 6 | |
| 7 | <a href="https://trendshift.io/repositories/25495" target="_blank"><img src="https://trendshift.io/api/badge/repositories/25495" alt="googleapis%2Fmcp-toolbox | Trendshift" style="width: 250px; height: 55px;" width="250" height="55"/></a> |
| 8 | |
| 9 | [](https://goreportcard.com/report/github.com/googleapis/mcp-toolbox) |
| 10 | [](https://opensource.org/licenses/Apache-2.0) |
| 12 | [](https://mcp-toolbox.dev/) |
| 13 | [](https://discord.gg/Dmm69peqjh) |
| 14 | [](https://medium.com/@mcp_toolbox) |
| 15 | |
| 16 | [](https://pypi.org/project/toolbox-core/) |
| 17 | [](https://www.npmjs.com/package/@toolbox-sdk/core) |
| 18 | [](https://pkg.go.dev/github.com/googleapis/mcp-toolbox-sdk-go) |
| 19 | [](https://mvnrepository.com/artifact/com.google.cloud.mcp/mcp-toolbox-sdk-java) |
| 20 | </div> |
| 21 | |
| 22 | MCP Toolbox for Databases is an open source Model Context Protocol (MCP) server that connects your AI agents, IDEs, and applications directly to your enterprise databases. |
| 23 | |
| 24 | <p align="center"> |
| 25 | <img src="docs/en/documentation/introduction/architecture.png" alt="architecture" width="50%"/> |
| 26 | </p> |
| 27 | |
| 28 | It serves a **dual purpose**: |
| 29 | 1. **Ready-to-use MCP Server (Build-Time):** Instantly connect Gemini CLI, Google Antigravity, Claude Code, Codex, or other MCP clients to your databases using our *prebuilt generic tools*. Talk to your data, explore schemas, and generate code without writing boilerplate. |
| 30 | 2. **Custom Tools Framework (Run-Time):** A robust framework to build specialized, highly secure AI tools for your production agents. Define structured queries, semantic search, and NL2SQL capabilities safely and easily. |
| 31 | |
| 32 | |
| 33 | This README provides a brief overview. For comprehensive details, see the [full documentation](https://mcp-toolbox.dev/). |
| 34 | |
| 35 | > [!IMPORTANT] |
| 36 | > **Repository Name Update:** The `genai-toolbox` repository has been officially renamed to `mcp-toolbox`. To ensure your local environment reflects the new name, you may update your remote: |
| 37 | > `git remote set-url origin https://github.com/googleapis/mcp-toolbox.git` |
| 38 | |
| 39 | > [!NOTE] |
| 40 | > This solution was originally named “Gen AI Toolbox for Databases” (github.com/googleapis/genai-toolbox) as its initial development predated MCP, but was renamed to align with the MCP compatibility. |
| 41 | |
| 42 | <!-- TOC ignore:true --> |
| 43 | ## Table of Contents |
| 44 | |
| 45 | - [Why MCP Toolbox?](#why-mcp-toolbox) |
| 46 | - [Quick Start: Prebuilt Tools](#quick-start-prebuilt-tools) |
| 47 | - [Quick Start: Custom Tools](#quick-start-custom-tools) |
| 48 | - [Install & Run the Toolbox server](#install--run-the-toolbox-server) |
| 49 | - [Connect to Toolbox](#connect-to-toolbox) |
| 50 | - [MCP Client](#mcp-client) |
| 51 | - [Toolbox SDKs: Integrate with your Application](#toolbox-sdks-integrate-with-your-application) |
| 52 | - [Additional Features](#additional-features) |
| 53 | - [Versioning](#versioning) |
| 54 | - [Contributing](#contributing) |
| 55 | - [Community](#community) |
| 56 | |
| 57 | --- |
| 58 | |
| 59 | ## Why MCP Toolbox? |
| 60 | |
| 61 | - **Out-of-the-Box Database Access:** Prebuilt generic tools for instant data exploration (e.g., `list_tables`, `execute_sql`) directly from your IDE or CLI. |
| 62 | - **Custom Tools Framework:** Build production-ready tools with your own predefined logic, ensuring safety through Restricted |
Related
6 picksType
- mcp-databricks-serverModel Context Protocol (MCP) server for Databricks that empowers AI agents to autonomously interact with Unity Catalog metadata. Enables data discovery, lineage analysis, and intelligent SQL execution.Mar 2026
- mcp-server-qdrantAn official Qdrant Model Context Protocol (MCP) server implementationJul 2026
- Supabase MCPQuery databases, manage projects and deploy edge functionstoday
- mongodb-mcp-serverMongoDB Model Context Protocol ServerJul 2026
- postgres-mcp-serverMCP server for interacting with PostgreSQL databasesJul 2025
- mcp-server-mysqlMCP server for interacting with MySQL databases with write operations supportJul 2026
