Ross ROSS = Recommend OSS · open-source software intelligence for agents

googleapis/mcp-toolbox

MCP Toolbox for Databases is an open source MCP server for databases. observed · 2026-08-28

github.com/googleapis/mcp-toolbox · homepage · Go · Apache-2.0 (permissive) observed · 2026-08-28

Health v2 · maintenance only

90/100

  • Activity 99
  • Release rhythm 97
  • Longevity 58
How is this computed?

round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10) — computed 2026-09-03. Adoption (stars, forks) is never an input.

  • gap_med: 14
  • age_days: 817
  • days_rel: 20
  • days_push: 7
  • n_releases_24m: 48

Full methodology

Adoption not part of the score

16262 stars · 1698 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-29, confidence not recorded

MCP Toolbox for Databases is an open source Model Context Protocol (MCP) server, written in Go, that connects AI agents, IDEs, and applications to enterprise databases. It offers prebuilt generic tools for instant data exploration plus a custom tools framework for defining secure, production-ready queries, semantic search, and NL2SQL capabilities via a tools.yaml configuration.

Use cases

  • connect Claude Code or Gemini CLI to my postgres database via MCP
  • let an AI agent query BigQuery or Spanner safely
  • build custom secure database tools for a production LLM agent
  • explore database schemas and run SQL from my IDE with an MCP client
  • add NL2SQL and semantic search tools to a LangChain or ADK agent
  • expose MongoDB or Elasticsearch data to AI agents with authentication

When to choose

  • you want a ready-made MCP server bridging AI agents/IDEs and many database engines
  • you need secure, parameterized, authenticated database tools for production agents
  • you use Google Cloud databases (BigQuery, Spanner, Firestore) or popular engines like Postgres, MySQL, MongoDB, Redis
  • you want connection pooling, IAM auth, and OpenTelemetry observability handled for you

When to avoid

  • you need a generic MCP server for non-database tools or APIs
  • you want a lightweight embedded library rather than a separately deployed server
  • your database engine is not among the supported sources
  • you require fully arbitrary LLM-generated SQL in production without developer oversight

Facets

service · maturity active

mcp database agent-framework api-framework auth monitoring search-engine databases large-language-models developer-tools backend self-hosted windows self-hosted go python cli mcp-server database-tools nl2sql genai tools-yaml bigquery postgresql mysql spanner firestore mongodb elasticsearch redis clickhouse langchain adk ai-agents linux macos docker nodejs

10 sources

Member repositories

RepositoryRoleHealth v2
googleapis/mcp-toolboxmain90

For agents

markdown · JSON · MCP: product_card(name="googleapis/mcp-toolbox")

Data as of 2026-08-30T08:39:29.467469+00:00 · Report a problem