What is the difference vs. Postgres MCP Pro or Supabase MCP?

Postgres MCP Pro and Supabase MCP are per-database specialists with deep tool surfaces. Google MCP Toolbox is a multi-database server defined declaratively in `tools.yaml`. Pick a per-DB MCP if you only touch one DB and want full depth; pick Toolbox when an agent needs to span Postgres + BigQuery + Redis (or similar) in one workflow.

Is it tied to Google Cloud?

No. It is published by `googleapis` and IAM-integrates with Google Cloud sources (AlloyDB, BigQuery, Spanner, Firestore), but it speaks Postgres, MySQL, SQL Server, MongoDB, Redis, Snowflake, ClickHouse, and more against any host. Apache-2.0; the binaries are public.

How do I limit what the agent can do?

Tools are defined explicitly in `tools.yaml`. If you only declare `list_tables` and `get_orders_by_id`, the agent only has those two tools — no ad-hoc SQL. This is the security thesis: declarative > generic `execute_sql`. Combine with a read-only DB user as defence in depth.

Four options: pre-compiled binary from `storage.googleapis.com/mcp-toolbox-for-databases/`, `brew install mcp-toolbox`, container at `us-central1-docker.pkg.dev/database-toolbox/toolbox/toolbox`, or `npx @toolbox-sdk/server --config tools.yaml`. Binary or container is the recommended path for production.

Yes — 15.6k stars, last push within the last 24 hours as of 2026-06-15, with a healthy release cadence. The repo was renamed from `genai-toolbox` to `mcp-toolbox` to reflect MCP-first positioning.

Google MCP Toolbox

Name: Top MCPs — curated MCP directory
Creator: Top MCPs
License: https://creativecommons.org/licenses/by/4.0/

Official

Google-published MCP server for databases — one Go binary speaks Postgres, MySQL, BigQuery, Spanner, AlloyDB, Snowflake, ClickHouse, MongoDB, Redis, and more.

Score 92(?)Google (googleapis)Apache-2.0 16kVerified Jun 15, 2026Top MCPs for Databases →

Install View on GitHub

Quick answer

What it does

Runs as a single Go binary (or container) that connects to one or more databases via a `tools.yaml` config and exposes them as MCP tools — prebuilt schema/query tools plus user-defined custom tools per source.

Best for

Multi-database agent workflows
Declarative `tools.yaml` query control
Google Cloud-native data (AlloyDB, BigQuery, Spanner, Firestore)
NL2SQL and RAG over enterprise data sources

Not for

Single-database setups already served by a per-DB MCP
Workflows where ad-hoc unconstrained SQL is required (use a per-DB MCP with read-only credentials)

Setup recipe

Pick your client, then follow the three steps.

Install

claude_desktop_config.jsonjson

{
  "mcpServers": {
    "google-mcp-toolbox": {
      "command": "brew",
      "args": [
        "install",
        "mcp-toolbox",
        "&&",
        "toolbox",
        "--tools-file",
        "tools.yaml"
      ]
    }
  }
}

Paste under mcpServers. Fully quit and reopen Claude after editing.

CLI or .mcp.jsonshell

claude mcp add google-mcp-toolbox -- brew install mcp-toolbox && toolbox --tools-file tools.yaml

Run from your repo. Commit .mcp.json to share with your team.

.cursor/mcp.jsonjson

{
  "mcpServers": {
    "google-mcp-toolbox": {
      "command": "brew",
      "args": [
        "install",
        "mcp-toolbox",
        "&&",
        "toolbox",
        "--tools-file",
        "tools.yaml"
      ]
    }
  }
}

Global path: ~/.cursor/mcp.json. Reload window after editing.

.vscode/mcp.jsonjsonc

{
  "servers": {
    "google-mcp-toolbox": {
      "command": "brew",
      "args": [
        "install",
        "mcp-toolbox",
        "&&",
        "toolbox",
        "--tools-file",
        "tools.yaml"
      ]
    }
  }
}

VS Code uses the "servers" key (not "mcpServers").

~/.codeium/windsurf/mcp_config.jsonjson

{
  "mcpServers": {
    "google-mcp-toolbox": {
      "command": "brew",
      "args": [
        "install",
        "mcp-toolbox",
        "&&",
        "toolbox",
        "--tools-file",
        "tools.yaml"
      ]
    }
  }
}

Open via Cascade → hammer icon → Configure.

cline_mcp_settings.jsonjson

{
  "mcpServers": {
    "google-mcp-toolbox": {
      "command": "brew",
      "args": [
        "install",
        "mcp-toolbox",
        "&&",
        "toolbox",
        "--tools-file",
        "tools.yaml"
      ]
    }
  }
}

Open via the Cline sidebar → MCP Servers → Edit.

~/.continue/config.jsonjson

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "brew",
          "args": [
            "install",
            "mcp-toolbox",
            "&&",
            "toolbox",
            "--tools-file",
            "tools.yaml"
          ]
        }
      }
    ]
  }
}

Continue uses modelContextProtocolServers with a transport block.

~/.codex/config.tomlshell

# ~/.codex/config.toml
[mcp_servers.google-mcp-toolbox]
command = "brew"
args = [
  "install",
  "mcp-toolbox",
  "&&",
  "toolbox",
  "--tools-file",
  "tools.yaml",
]

Codex uses TOML. Each server is a [mcp_servers.<name>] subtable.

~/.config/zed/settings.jsonjsonc

{
  "context_servers": {
    "google-mcp-toolbox": {
      "command": {
        "path": "brew",
        "args": [
          "install",
          "mcp-toolbox",
          "&&",
          "toolbox",
          "--tools-file",
          "tools.yaml"
        ]
      }
    }
  }
}

Zed calls them "context_servers". Settings live-reload on save.

ChatGPT → Apps directorynone

Google MCP Toolbox doesn't ship a hosted HTTPS endpoint today. ChatGPT supports remote MCP servers only — to use this server in ChatGPT you'll need to deploy it to a public HTTPS URL first (e.g. via Cloudflare Workers or Vercel) or wait for an official remote build.

2
Set required secrets
No credentials required — this MCP runs over stdio without authentication.
3
Try a minimum working prompt
Cross-database lookup: Postgres user + BigQuery activity
Using the MCP Toolbox, look up user 42 in Postgres (`get_user_by_id`), then pull their last 30 days of events from BigQuery (`get_recent_events`). Return name, email, event count, and the top three event types.
Tested with: Claude Code, Cursor, Claude Desktop.

Tools & permissions

Tools list pending verification. The server exposes tools over MCP; we haven’t yet parsed its capability manifest into this page. Check the GitHub repo for the authoritative list.

Security & scope

Access scope: Read + write
Sandbox: Tools are explicitly declared in `tools.yaml`. Only the queries you define are callable by the agent — there is no implicit `execute_sql` unless you add it. Connections use the DB host's native auth (Postgres roles, BigQuery IAM, MongoDB users, etc.).
Gotchas: A generic `execute_sql` tool in `tools.yaml` is the same risk surface as direct DB access — only add it for read-only DB users on dev/staging.
IAM-bound Google Cloud sources inherit the service account or user credentials of the running binary — scope the binary's identity tightly, not your personal account.
The streamable-HTTP endpoint (`:5000/mcp`) binds to localhost by default; if you expose it on a network, gate it behind auth at the network or proxy layer.

Agent prompt pack

— copy into Claude, Cursor, or ChatGPT.

Paste into Claude, Cursor, or ChatGPT. Edit the [brackets] before sending.

Recommend the best MCP servers for [task: e.g. databases work] in [client: Claude].

Constraints:
- Prefer tools that are [official | open-source | read-only] — pick what matters for my use case.
- Exclude MCPs that require [e.g. a paid plan, OAuth-only flows, remote-only transport].
- Return at most 3 picks, ranked.

For each pick include:
1. One-sentence rationale.
2. The ready-to-paste install snippet for my client.
3. Any required secrets I need to create before installing.

Cross-check the top-mcps.com listing: https://top-mcps.com/top-mcps-for-databases

Compare Google MCP Toolbox against a real alternative. Swap the second MCP in [brackets] if you want a different match.

Compare Google MCP Toolbox MCP vs [Postgres MCP Pro MCP] for the following job: [describe the job, e.g. "let an agent create GitHub issues on bug triage"].

Judge them on:
- Setup time and complexity (what a new user hits first).
- Auth model (none / API key / OAuth 2.1) and credential risk.
- Transport (stdio / Streamable HTTP / SSE) and where the server runs.
- Required secrets and the blast radius if they leak.
- Operational risk in an unattended agent loop.
- Which one is "good enough" for a weekend prototype vs. production.

End with one sentence: which should I pick for my scenario, which is: [my scenario].

References:
- https://top-mcps.com/mcp/google-mcp-toolbox
- top-mcps.com listing for Postgres MCP Pro

Asks the agent to install and verify. Works inside Claude Code, Cursor Agent, Codex CLI.

Install the Google MCP Toolbox MCP server for my [client: Claude] at the default config path for that client.

Use the exact install snippet published at https://top-mcps.com/mcp/google-mcp-toolbox (fetch https://top-mcps.com/mcp/google-mcp-toolbox.json for the canonical server.json if you can read URLs).

Before finishing:
1. Create the required secrets (no secrets) and put them in the appropriate env block — do not hard-code them.
2. Restart or reload the client so it picks up the new server.
3. Verify the server is connected (green / running state) and at least one tool is listed.
4. If anything fails, read the client's MCP logs and report the exact error — do not silently retry.

Confirm when done and list the tools the server now exposes.

Frequently asked questions

What changed

— 2 updates tracked.

Jun 15, 2026
Refreshed install snippets and fact sheet; verified for 2026.
Apr 9, 2025
Initial directory listing.

At a glance

Maintainer: Google (googleapis)
Transport: stdioStreamable HTTP
Auth model: API key
Required secrets: None
Supported clients: ChatGPT
Claude Desktop
Claude Code
Cursor
VS Code
Windsurf
Cline
Continue
Zed
Codex CLI
License: Apache-2.0
Language: Go
Latest version: latest
Last verified: Jun 15, 2026

GitHub repo Official website

Alternatives

Postgres MCP Pro →
Production-grade Postgres MCP with index advice, EXPLAIN, and health checks.
Supabase →
Full Supabase access: database, auth, storage, and edge functions.
BigQuery →
Query Google BigQuery datasets from Claude, Cursor, and VS Code.
Snowflake →
Inspect schemas and run SQL against a Snowflake account from an AI agent.
ClickHouse →
Query ClickHouse and ClickHouse Cloud columnar warehouses from an AI agent.
MongoDB →
Query and inspect MongoDB collections from Claude, Cursor, and VS Code.
Redis →
Inspect keys, run commands, and debug Redis from an AI agent.

More Databases MCPs

Other tools in the same category worth evaluating.

Postgres MCP Pro

Production-grade Postgres MCP with index advice, EXPLAIN, and health checks.

databasesqlpostgresperformance

5 minMedium

SQLite

Local SQLite database access with full read/write support.

databasesqlitelocalstorage

2 minLow

Supabase

Full Supabase access: database, auth, storage, and edge functions.

supabasedatabasebackendpostgres

5 minLow

Compared with Google MCP Toolbox

Side-by-side breakdowns for the choices people most often weigh against this MCP.

Google MCP ToolboxvsPostgres MCP Pro Google MCP ToolboxvsSupabase Google MCP ToolboxvsBigQuery Google MCP ToolboxvsSnowflake

Exploring Top MCPs for Databases? See all Databases MCPs →