M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
M

MCP Toolbox for Databases

Official
Google's official database MCP toolbox — define AI-accessible database tools via config
How to install ↓ Compare GitHub source repository ↗
Category
Database #3 of 58
Stars
★ 16.7k Very popular
Transport
stdio (local process) · Streamable HTTP
Runtime
Node.js · Prebuilt binary · Docker
Credentials
API key / credential required
License
Apache-2.0
Last commit
74FMRS · B

Officially maintained by Google; the config-driven design allows finer-grained permission control than a fixed-tool-list database MCP, but security depends heavily on how tools.yaml is written. The tool list varies by configuration, so no fixed tools field is listed. This review is a static check of source and docs, not an actual connection test.

Strongest · Maintenance 17/20 Weakest · Reliability 13/20

Reliability
13/20
Security and permissions
13/20
Maintenance
17/20
Documentation
16/20
Setup experience
15/20

Test out of dateListed 2026-07-24

Read the FMRS scoring method →

Fit and risk

What it can accessConnects to a database

Best for

  • Teams that want precise control over which database operations an AI can perform, rather than open arbitrary SQL execution
  • Scenarios needing a unified MCP setup across multiple database engines

Not for

  • Lightweight cases that just want to run a few ad-hoc SQL queries without maintaining a tools.yaml config (a simpler single-database MCP may be a better fit)

Required permissions

  • Database credentials (username/password/connection string) are supplied via env vars or config
  • A tool's actual permission is whatever SQL statement is defined in tools.yaml — designed for least privilege, but misconfiguration can still over-expose access

Risks and side effects

  • If tools.yaml defines SQL statements that allow unconstrained writes or deletes, the AI could accidentally modify data
  • The prebuilt toolsets (--prebuilt) favor convenience and may expose broader query capability than a specific business actually needs — use a custom tools.yaml in production

Setup

Before you start

Runtime：Node.js · Prebuilt binary · Docker

1) Quick start: npx -y @toolbox-sdk/server --prebuilt=postgres --stdio with the matching database connection env vars gives you a prebuilt tool set.
2) Custom: write a tools.yaml defining specific SQL tools and toolsets, run the Docker image us-central1-docker.pkg.dev/database-toolbox/toolbox/toolbox in Streamable HTTP mode with the config file mounted.

.mcp.json 
{
  "mcpServers": {
    "toolbox-postgres": {
      "command": "npx",
      "args": ["-y", "@toolbox-sdk/server", "--prebuilt=postgres", "--stdio"]
    }
  }
}

Shown for Claude Code. Other clients may use a different file or key (VS Code uses "servers") — the configurator below converts it.

.vscode/mcp.json
{
  "servers": {
    "toolbox-postgres": {
      "command": "npx",
      "args": [
        "-y",
        "@toolbox-sdk/server",
        "--prebuilt=postgres",
        "--stdio"
      ]
    }
  }
}

Goes in your project's .vscode/mcp.json (VS Code uses a "servers" key).

Terminal
claude mcp add toolbox-postgres -- npx -y @toolbox-sdk/server --prebuilt=postgres --stdio

Run it in a terminal; replace any <…> placeholders with your own values first.

Generate and validate client config

Check that it works

After starting with e.g. npx @toolbox-sdk/server --prebuilt=postgres --stdio, prebuilt database tools such as list_tables and execute_sql should appear in the client's tool list; asking it to "list all tables" and getting real table names confirms the connection.

Troubleshooting

  1. Prebuilt toolset fails to connect: check that the matching database's env vars (e.g. connection string) are set correctly
  2. Custom config not taking effect: confirm the path passed to --config or --config-folder is accessible inside the container
  3. Streamable HTTP connection times out: check port mapping and firewall settings

Things to try

Once connected, you can ask your AI assistant things like:

  • List all tables in my Postgres database
  • Show me the schema of the hotels table
  • Run a query to fetch the first 10 rows from the hotels table

Use cases

Let an AI assistant run pre-reviewed, read-only queries instead of executing arbitrary SQL
Define different-permission toolsets for different agents/apps
Provide one unified AI access point across multiple database types (Postgres, MySQL, SQLite, etc.)

Supported clients

Claude Code
Gemini CLI
Zed
Antigravity

Listed from the project's documentation, not tested by this site.

Overview

An open-source MCP server officially maintained by Google for connecting AI assistants to databases. Unlike database MCP servers with a fixed tool list, MCP Toolbox is config-driven: a tools.yaml file defines exactly which SQL queries are exposed as tools (name, parameters, SQL statement), grouped into toolsets. It also ships ready-to-use --prebuilt=<database> toolsets (e.g. postgres/mysql) for a quick start without hand-writing config.

Similar servers

Compare with other MCP servers

Source revision 6d46c5f39df8 Data synced 2026-10-19 Read the FMRS scoring method