googleapis/mcp-toolbox

MCP Toolbox for Databases is an open source MCP server for databases.

MCP Toolbox for Databases – Quick Overview

What it is – An open‑source Model Context Protocol (MCP) server that sits between AI agents (or IDEs) and enterprise databases. It lets LLM‑powered tools talk to a database without the developer writing low‑level connection code.

Key capabilities

  • Pre‑built tools (e.g. list_tables, execute_sql) that can be enabled with a single flag for many popular databases (PostgreSQL, MySQL, BigQuery, Spanner, MongoDB, Snowflake, …). Agents can issue natural‑language queries and get results back.
  • Custom‑tool framework – Define your own tools.yaml with sources, tools, toolsets, prompts and read‑only resources. The server validates the configuration, enforces structured queries, and isolates access.
  • Multi‑language SDKs – Python, JavaScript/TypeScript, Go, Java client libraries make it easy to load a toolset from an application or a LangChain/LlamaIndex agent.
  • Built‑in security & observability – IAM‑based authentication, connection pooling, OpenTelemetry metrics/traces.

How you use it

  1. Install – binary, Docker image, Homebrew, or npx @toolbox-sdk/server.
  2. Run – toolbox --config tools.yaml (or --prebuilt=postgres).
  3. Connect – add the server URL to an MCP‑compatible client (Gemini CLI, Claude Code, etc.) or use one of the SDKs to load a toolset in code.
  4. Interact – ask the LLM “show me the top 10 customers” and the server translates the request into a safe SQL statement against the configured source.

Why it matters – It removes the boilerplate and security risk of letting an LLM run arbitrary SQL, while still giving agents the ability to retrieve and manipulate data programmatically. Ideal for building production‑grade AI assistants, data‑exploration bots, or code‑generation tools that need reliable database access.

Links

Related

  • Project
    IBM/mcp

    A collection of Model Context Protocol (MCP) servers and tools that enable AI agents to securely interact with IBM products, enterprise data, and cloud infrastructure.

  • Project
    microsoft/mcp

    The Model Context Protocol (MCP) is an open standard that enables AI applications to connect to data sources and tools consistently. This repository provides the core infrastructure and a collection of official Microsoft servers to integrate services like Azure, GitHub, and Microsoft 365 with AI agents.

  • Project
    salesforcecli/mcp

    An MCP server that enables LLMs and AI agents to securely read, manage, and operate Salesforce orgs through a standardized set of tools.

  • Project
    dbt-labs/dbt-mcp

    dbt‑MCP Server is an open‑source service that exposes a large catalog of dbt‑related tools (SQL execution, semantic‑layer queries, model discovery, dbt CLI commands, job administration, code generation, and documentation lookup) via the Model Context Protocol. It lets LLM‑powered agents understand and act on a dbt project—generating SQL from natural language, running dbt jobs, fetching lineage, and even creating new model files—making it a concrete bridge between data‑engineering metadata and AI assistants.

  • Project
    FreePeak/db-mcp-server

    A multi-database server implementing the Model Context Protocol (MCP) that provides AI assistants with structured and secure access to multiple databases.