{"data":{"slug":"googleapis-mcp-toolbox","name":"mcp-toolbox","tagline":"MCP Toolbox for Databases is an open source server enabling database-aware interactions and code generation via AI agents.","github_url":"https://github.com/googleapis/mcp-toolbox","owner":"googleapis","repo":"mcp-toolbox","owner_avatar_url":"https://avatars.githubusercontent.com/u/16785467?v=4","primary_language":"Go","stars":16197,"forks":1686,"topics":["agent","agents","ai","bigquery","clickhouse","cockroachdb","database","elasticsearch","firestore","genai","llm","mcp","mongodb","mysql","oracle","postgresql","redis","server","spanner","tidb"],"archived":false,"github_pushed_at":"2026-08-19T04:01:42+00:00","maintenance_label":"Very active","stars_delta_30d":217,"url":"https://www.graphcanon.com/tools/googleapis-mcp-toolbox","markdown_url":"https://www.graphcanon.com/tools/googleapis-mcp-toolbox.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/googleapis-mcp-toolbox","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=googleapis-mcp-toolbox","description":"MCP Toolbox for Databases is an open source MCP server for databases.","homepage_url":"https://mcp-toolbox.dev/documentation/introduction/","license":"Apache-2.0","open_issues":242,"watchers":87,"ai_summary":"The repository provides a comprehensive MCP (Machine Communication Protocol) server tool suite designed to facilitate database interaction through artificial intelligence features. It supports multiple databases, offers schema discovery, manages automation of common tasks, and enables the creation of database-aware code snippets, all while integrating seamlessly with various IDEs and client applications.","readme_excerpt":"## Quick Start: Prebuilt Tools\n\nStop context-switching and let your AI assistant become a true co-developer. By connecting your IDE to your databases with MCP Toolbox, you can query your data in plain English, automate schema discovery and management, and generate database-aware code.\n\nYou can use the Toolbox in any MCP-compatible IDE or client (e.g., Gemini CLI, Google Antigravity, Claude Code, Codex, etc.) by configuring the MCP server.\n\n**Prebuilt tools are also conveniently available via the [Google Antigravity MCP Store](https://antigravity.google/docs/mcp) with a simple click-to-install experience.**\n\n1. Add the following to your client's MCP configuration file (usually `mcp.json` or `claude_desktop_config.json`):\n\n    ```json\n    {\n      \"mcpServers\": {\n        \"toolbox-postgres\": {\n          \"command\": \"npx\",\n          \"args\": [\n            \"-y\",\n            \"@toolbox-sdk/server\",\n            \"--prebuilt=postgres\",\n            \"--stdio\"\n          ]\n        }\n      }\n    }\n    ```\n\n2. Set the appropriate environment variables to connect, see the [Prebuilt Tools Reference](https://mcp-toolbox.dev/documentation/configuration/prebuilt-configs/).\n\nWhen you run Toolbox with a `--prebuilt=<database>` flag, you instantly get access to standard tools to interact with that database. You can also specify a specific toolset using the `--prebuilt=<database>/<toolset>` syntax (e.g., `--prebuilt=postgres/data` to only load SQL tools). \n\nSupported databases currently include:\n- **Google Cloud:** AlloyDB, BigQuery, Cloud SQL (PostgreSQL, MySQL, SQL Server), Spanner, Firestore, Knowledge Catalog (formerly known as Dataplex).\n- **Other Databases:** PostgreSQL, MySQL, [MariaDB](https://mcp-toolbox.dev/integrations/mariadb/source/), SQL Server, Oracle, MongoDB, Redis, Elasticsearch, CockroachDB, ClickHouse, Couchbase, Neo4j, Snowflake, Trino, and more.\n\nFor a full list of available tools and their capabilities across all supported databases, see the [Prebuilt Tools Reference](https://mcp-toolbox.dev/documentation/configuration/prebuilt-configs/).\n\n*See the [Install & Run the Toolbox server](#install--run-the-toolbox-server) section for different execution methods like Docker or binaries.*\n\n\n> [!TIP]\n> For users looking for a managed solution, [Google Cloud MCP Servers](https://cloud.google.com/blog/products/databases/managed-mcp-servers-for-google-cloud-databases) \n> provide a managed MCP experience with prebuilt tools; you can [learn more about the differences here](https://mcp-toolbox.dev/dev/reference/faq/).\n\n---\n\n---\n\n## Quick Start: Custom Tools\n\nToolbox can also be used as a framework for customized tools.\nThe primary way to configure Toolbox is through the `tools.yaml` file. If you\nhave multiple files, you can tell Toolbox which to load with the `--config\ntools.yaml` flag.\n\nYou can find more detailed reference documentation to all resource types in the\n[Resources](https://mcp-toolbox.dev/documentation/configuration/).\n\n---\n\n## Install & Run the Toolbox server\n\nYou can run Toolbox directly with a [configuration file](#quick-start-custom-tools):\n\n```sh\nnpx @toolbox-sdk/server --config tools.yaml\n```\n\nThis runs the latest version of the Toolbox server with your configuration file.\n\n> [!NOTE]\n> This method is optimized for convenience rather than performance. \n> For a more standard and reliable installation, please use the binary\n> or container image as described in [Install & Run the Toolbox server](#install--run-the-toolbox-server).\n\n---\n\n### Install Toolbox\n\nFor the latest version, check the [releases page][releases] and use the\nfollowing instructions for your OS and CPU architecture.\n\n[releases]: https://github.com/googleapis/mcp-toolbox/releases\n\n<details open>\n<summary>Binary</summary>\n\nTo install Toolbox as a binary:\n\n\n> <details>\n> <summary>Linux (AMD64)</summary>\n>\n> To install Toolbox as a binary on Linux (AMD64):\n>\n> ```sh\n> # see releases page for other versions\n> export VERSION=1.9.0\n> curl -L -o toolbox https://storage.goo","github_created_at":"2024-06-07T20:52:54+00:00","created_at":"2026-07-07T17:38:54.482457+00:00","updated_at":"2026-08-19T06:01:10.422876+00:00","categories":[{"slug":"ai-agents","name":"AI Agents","url":"https://www.graphcanon.com/categories/ai-agents","markdown_url":"https://www.graphcanon.com/categories/ai-agents.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/ai-agents"},{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"}],"tags":[{"slug":"agent","name":"agent"},{"slug":"agents","name":"agents"},{"slug":"ai","name":"ai"},{"slug":"bigquery","name":"bigquery"},{"slug":"clickhouse","name":"clickhouse"},{"slug":"cockroachdb","name":"cockroachdb"},{"slug":"database","name":"database"},{"slug":"elasticsearch","name":"elasticsearch"}],"trust":{"provenance":{"is_fork":false,"github_id":812044182,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-19T06:01:09.609Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":7,"days_since_push":0,"last_release_at":"2026-08-14T01:16:16Z","stars_delta_30d":217,"open_issues_delta_30d":-5},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":14,"high_count":0,"last_scan_at":"2026-07-11T11:13:25.774Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"mcp":{"source":"repo_scan","observed_at":"2026-08-19T06:01:10.095Z","server_manifest":false},"scan":{"source":"repo_scan","observed_at":"2026-08-19T06:01:10.095Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-08-19T06:01:10.095Z","managed_saas":false},"languages":{"value":["go"],"source":"github.language","observed_at":"2026-08-19T06:01:10.095Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-08-19T06:01:10.095Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-08-19T06:01:10.095Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["- Use when you need to automate schema discovery, management, and code generation specific to your database.","- Optimal if your project heavily involves interaction with multiple database systems supported by MCP (like PostgreSQL, MySQL, MongoDB, Redis).","- Ideal for environments where there's a requirement to integrate seamlessly with IDEs through an MCP server."],"when_not_to_use":["- Avoid if your IDE or client is not compatible with the MCP protocol.","- If you're looking for managed services rather than self-hosted solutions, as MCP Toolbox requires local setup and configuration.","- Not recommended if your development workflow strictly adheres to non-Google ecosystem tools and integrations."],"source":"enrich:decision_facts","observed_at":"2026-07-11T14:49:15.174Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"MCP Toolbox for Databases is an open-source tool that connects IDEs with multiple databases and automates tasks through AI features."}]}}