{
  "markdown": "# Dataproc\n\n> [!NOTE]\n> Currently in beta (pre-v1.0), and may see breaking changes until the first stable release (v1.0).\n\nThis repository packages [MCP Toolbox](https://github.com/googleapis/mcp-toolbox)'s prebuilt `dataproc` server as a plugin/extension to interact with [Dataproc](https://cloud.google.com/dataproc) clusters and jobs. It can be used with various AI agents, including [Antigravity](https://antigravity.google/), [Claude Code](https://claude.com/product/claude-code) and [Codex](https://developers.openai.com/codex), to manage your clusters, monitor jobs, and troubleshoot issues using natural language prompts.\n\n> [!IMPORTANT]\n> **We Want Your Feedback!**\n> Please share your thoughts with us by filling out our feedback [form][form].\n> Your input is invaluable and helps us improve the project for everyone.\n\n[form]: https://docs.google.com/forms/d/e/1FAIpQLSfEGmLR46iipyNTgwTmIDJqzkAwDPXxbocpXpUbHXydiN1RTw/viewform?usp=pp_url&entry.157487=dataproc\n\n## Table of Contents\n\n- [Why Use Dataproc?](#why-use-dataproc)\n- [Prerequisites](#prerequisites)\n- [Getting Started](#getting-started)\n  - [Configuration](#configuration)\n  - [Installation & Usage](#installation--usage)\n    - [Antigravity](#antigravity)\n    - [Claude Code](#claude-code)\n    - [Codex](#codex)\n- [Installing via a compatible Agent Plugins client](#installing-via-a-compatible-agent-plugins-client)\n- [Usage Examples](#usage-examples)\n- [Available Tools](#available-tools)\n- [Generating Skills Instead](#generating-skills-instead)\n- [Troubleshooting](#troubleshooting)\n\n## Why Use Dataproc?\n\n- **Seamless Workflow:** Integrates seamlessly into your AI agent's environment. No need to constantly switch contexts for common Dataproc tasks.\n- **Natural Language Queries:** Stop wrestling with complex gcloud commands. Manage your clusters and jobs by describing what you want in plain English.\n- **Full Lifecycle Control:** Manage the entire lifecycle of your Dataproc resources, from listing clusters to checking job statuses.\n\n## Prerequisites\n\nBefore you begin, ensure you have the following:\n\n- One of these AI agents installed\n  - Antigravity\n     - [Antigravity CLI](https://github.com/google-gemini/gemini-cli) version **v1.6.0** or higher\n     - [Antigravity 2.0](https://antigravity.google/product/antigravity-2) version **v2.0.0** or higher.\n  - [Claude Code](https://claude.com/product/claude-code) version **v2.1.94** or higher.\n  - [Codex](https://developers.openai.com/codex) **v0.117.0** or higher.\n- [Node.js](https://nodejs.org/) — the MCP server runs via `npx`.\n- A Google Cloud project with the **Dataproc API** enabled.\n- Ensure [Application Default Credentials](https://cloud.google.com/docs/authentication/gcloud) are available in your environment.\n- IAM Permissions:\n  - Dataproc Viewer (`roles/dataproc.viewer`) or Dataproc Editor (`roles/dataproc.editor`)\n\n## Getting Started\n\n### Configuration\n\nPlease keep these env vars handy during the installation process:\n\n- `DATAPROC_PROJECT`: The GCP project ID.\n- `DATAPROC_REGION`: The region of your Dataproc resources.\n\n> [!NOTE]\n>\n> - Ensure [Application Default Credentials](https://cloud.google.com/docs/authentication/gcloud) are available in your environment.\n> - If your Cloud SQL for PostgreSQL instance uses private IPs, you must run your agent in the same Virtual Private Cloud (VPC) network.\n\n\n### Installation & Usage\n\nTo start interacting with your database, install the extension for your preferred AI agent, then launch the agent and use natural language to ask questions or perform tasks.\n\nFor the latest version, check the [releases page][releases].\n\n[releases]: https://github.com/gemini-cli-extensions/dataproc/releases\n\n<!-- {x-release-please-start-version} -->\n\n<details open>\n<summary id=\"antigravity\">Antigravity</summary>\n\nYou can use either of these two agents for Antigravity:\n- [Antigravity CLI](https://github.com/google-gemini/gemini-cli) version **v1.6.0** or higher\n- [Antigravity 2.0](https://antigravity.google/product/antigravity-2) version **v2.0.0** or higher.\n\n<blockquote>\n💡 <strong>Tip — Migrating from Gemini CLI?</strong><br>\nIf you previously installed this extension with <code>gemini extensions install</code>, you can convert it to an Antigravity plugin instead of reinstalling from scratch:\n<ul>\n  <li><strong>On first launch of Antigravity CLI</strong>, accept the Migration Options prompt to automatically convert your installed Gemini CLI extensions to Antigravity plugins.</li>\n  <li><strong>Or, from your terminal</strong>, run:\n    <pre><code class=\"language-bash\">agy plugin import gemini</code></pre>\n  </li>\n</ul>\nSee <a href=\"https://antigravity.google/docs/gcli-migration\">Migrating from Gemini CLI</a> for details on plugins, context files (<code>GEMINI.md</code> / <code>AGENTS.md</code>), and MCP server config differences.\n</blockquote>\n\n#### Antigravity 2.0 (IDE)\n\n**1. Install the plugin:**\n\nInstall the plugin directly from the remote GitHub repository:\n\n```bash\nagy plugin install https://github.com/gemini-cli-extensions/dataproc\n```\n\n**2. Set env vars:**\nSet your environment vars as described in the [configuration section](#configuration).\n\n_(Tip: You can verify the MCP server is active by running the `/mcp` command in your active session.)_\n\n#### Antigravity CLI\n\nYou can install plugins directly from a remote GitHub repository.\n\n**1. Install the plugin:**\n\n```bash\nagy plugin install https://github.com/gemini-cli-extensions/dataproc\n```\n\n**2. Set env vars:**\nSet your environment vars as described in the [configuration section](#configuration).\n\n</details>\n\n<details>\n<summary id=\"claude-code\">Claude Code</summary>\n\n**1. Set env vars:**\nIn your terminal, set your environment vars as described in the [configuration section](#configuration).\n\n**2. Start the agent:**\n\n```bash\nclaude\n```\n\n**3. Install the plugin:**\n\n```bash\n/plugin install dataproc@claude-plugins-official\n```\n\n_(Tip: Run `/plugin list` inside Claude Code to verify the plugin is active, or `/reload-plugins` if you just installed it.)\n</details>\n\n<details>\n<summary id=\"codex\">Codex</summary>\n\n**1. Install marketplace:**\n\n```bash\ncodex plugin marketplace add GoogleCloudPlatform/data-agent-kit\n```\n\n**2. Install the plugin:**\n\n```bash\ncodex plugin add dataproc@data-agent-kit\n```\n\n**3. Set env vars:**\nEnter your environment vars as described in the [configuration section](#configuration).\n\n**4. (Optional) Update the marketplace:**\n```sh\ncodex plugin marketplace upgrade data-agent-kit\n```\n\n</details>\n\n## Installing via a compatible Agent Plugins client\n## Installing via a compatible Agent Plugins client\n\nThis repository is a valid [Agent Plugins](https://github.com/agentplugins/agent-plugins-spec) (v1) plugin. Any [Agent Plugins–compatible client](https://agent-plugins.org/compatible-clients) can install it directly using its own built-in plugin command — no extra tooling required — by pointing at this repository:\n\n```\nhttps://github.com/gemini-cli-extensions/dataproc\n```\n\nBeyond harnesses covered by the native install above, compatible clients include VS Code, Cursor, GitHub Copilot, and Kiro. See your agent's documentation for its exact install command.\n\n**Set env vars:**\nSet your environment vars as described in the [configuration section](#configuration).\n\n<!-- {x-release-please-end} -->\n\n## Usage Examples\n\nInteract with Dataproc using natural language:\n\n- **List Clusters:**\n  - \"List all my Dataproc clusters in us-central1.\"\n- **Check Jobs:**\n  - \"Show me the status of the job with ID 'my-spark-job-123'.\"\n  - \"List all failed jobs in my project.\"\n- **Get Details:**\n  - \"Get details for the cluster named 'my-cluster'.\"\n\n## Available Tools\n\nThe tools come from MCP Toolbox's prebuilt `dataproc` server, grouped into toolsets:\n\n- **dataproc_tools** - Skills to interact with your Dataproc clusters and jobs.\n\nFor the full, up-to-date list, see the [`dataproc` prebuilt config](https://github.com/googleapis/mcp-toolbox/blob/main/internal/prebuiltconfigs/tools/dataproc.yaml)\nin the MCP Toolbox repository.\n\n## Generating Skills Instead\n\nThe tool-backed skills this plugin used to ship were generated from the same prebuilt\ntoolsets. If your agent lacks deferred tool loading, or you prefer skills, regenerate\nthem with the script in this repository:\n\n```bash\nVERSION=<toolbox version> ./.github/scripts/generate_skills.sh\n```\n\nUse the toolbox version pinned in [`mcp.json`](./mcp.json). A single toolset, without\nthe script:\n\n```bash\nnpx @toolbox-sdk/server@<toolbox version> --prebuilt dataproc skills-generate \\\n  --name \"<skill name>\" \\\n  --toolset \"<toolset>\" \\\n  --description \"<what it is for>\"\n```\n\nThe generated scripts call the toolbox through `npx`, so no binary download is needed.\nSee [Generate Agent Skills](https://github.com/googleapis/mcp-toolbox#generate-agent-skills)\nin the MCP Toolbox repository.\n\n## Troubleshooting\n\nUse the debug mode of your agent (e.g., `gemini --debug`) to enable debugging.\n\nCommon issues:\n\n- \"failed to find default credentials\": Ensure [Application Default Credentials](https://cloud.google.com/docs/authentication/gcloud) are available in your environment.\n- \"cannot execute binary file\": The Toolbox binary did not download correctly.\n",
  "bytes": 9210,
  "sha": "73e4cbbe44dc37cf20c364e6d0abd4c514e23b7496ae7c8bcdfc4669ec70d827",
  "repo_slug": "gemini-cli-extensions/dataproc",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/plg_gemini_cli_extensions_dataproc_f982612e/readme"
}