{"id":44588779,"url":"https://github.com/databricks-solutions/databricks-exec-code-mcp","last_synced_at":"2026-02-14T06:34:55.784Z","repository":{"id":333466797,"uuid":"1114989785","full_name":"databricks-solutions/databricks-exec-code-mcp","owner":"databricks-solutions","description":null,"archived":false,"fork":false,"pushed_at":"2026-02-03T15:03:08.000Z","size":96,"stargazers_count":8,"open_issues_count":1,"forks_count":3,"subscribers_count":1,"default_branch":"main","last_synced_at":"2026-02-04T04:58:40.199Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"other","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/databricks-solutions.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":"NOTICE.md","maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-12-12T07:19:52.000Z","updated_at":"2026-02-04T00:45:02.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/databricks-solutions/databricks-exec-code-mcp","commit_stats":null,"previous_names":["databricks-solutions/databricks-exec-code-mcp"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/databricks-solutions/databricks-exec-code-mcp","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databricks-solutions%2Fdatabricks-exec-code-mcp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databricks-solutions%2Fdatabricks-exec-code-mcp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databricks-solutions%2Fdatabricks-exec-code-mcp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databricks-solutions%2Fdatabricks-exec-code-mcp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/databricks-solutions","download_url":"https://codeload.github.com/databricks-solutions/databricks-exec-code-mcp/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/databricks-solutions%2Fdatabricks-exec-code-mcp/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29438799,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-14T05:24:35.651Z","status":"ssl_error","status_checked_at":"2026-02-14T05:24:34.830Z","response_time":53,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2026-02-14T06:34:55.053Z","updated_at":"2026-02-14T06:34:55.769Z","avatar_url":"https://github.com/databricks-solutions.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"## Databricks MCP Code Execution Template\n\nThis template enables AI-assisted development in Databricks by leveraging the Databricks Command Execution API through an MCP server. Test code directly on clusters, then deploy with Databricks Asset Bundles (DABs).\n\n### 🎯 What This Does\n\n- ✅ Run and test code directly on Databricks clusters\n- ✅ Auto-select clusters - no need to specify a cluster ID\n- ✅ Create and deploy Databricks Asset Bundles (DABs)\n- ✅ All from natural language prompts!\n\n**Just describe what you want → AI builds, tests the code on Databricks, and deploys the complete pipeline.**\n\n---\n\n### 🚀 Quick Start (Recommended Workflow)\n\n#### Step 1: Set Up the MCP Server (One Time)\n\nClone and set up the MCP server somewhere on your machine:\n\n```bash\ngit clone https://github.com/databricks-solutions/databricks-exec-code-mcp.git\ncd databricks-exec-code-mcp\npython -m venv .venv\nsource .venv/bin/activate\npip install -r requirements.txt\n```\n\n#### Step 2: Configure Databricks Credentials\n\nAdd to your `~/.zshrc` or `~/.bashrc`:\n\n```bash\nexport DATABRICKS_HOST=https://your-workspace.cloud.databricks.com\nexport DATABRICKS_TOKEN=dapi_your_token_here\n```\nMake sure the variables are loaded:\n\n```\nsource ~/.zshrc\n````\n\n**To get your Personal Access Token (PAT):** Databricks workspace → Profile → Settings → Developer → Access Tokens → Generate new token\n\n#### Step 3: Start a New Project\n\nCreate your project directory and install the Databricks skills:\n\n```bash\n# Create and enter your project\nmkdir my-databricks-project \u0026\u0026 cd my-databricks-project\n\n# Initialize git in your my-databricks-project project\ngit init .\n\n# Install skills for your AI client (downloads from remote)\ncurl -sSL https://raw.githubusercontent.com/databricks-solutions/databricks-exec-code-mcp/main/install_skills.sh | bash -s -- --cursor\n# Or for Claude Code:\ncurl -sSL https://raw.githubusercontent.com/databricks-solutions/databricks-exec-code-mcp/main/install_skills.sh | bash -s -- --claude\n# Or for both:\ncurl -sSL https://raw.githubusercontent.com/databricks-solutions/databricks-exec-code-mcp/main/install_skills.sh | bash -s -- --all\n```\n\nThis creates:\n- **Cursor**: `.cursor/rules/` with Databricks rules\n- **Claude Code**: `.claude/skills/` with Databricks skills\n\n#### Step 4: Configure Your AI Client\n\nPoint your AI client to the MCP server you set up in Step 1.\n\n**For Cursor** — create `.cursor/mcp.json` in your project:\n```json\n{\n  \"mcpServers\": {\n    \"databricks\": {\n      \"command\": \"/path/to/databricks-exec-code-mcp/.venv/bin/python\",\n      \"args\": [\"/path/to/databricks-exec-code-mcp/mcp_tools/tools.py\"]\n    }\n  }\n}\n```\n\n**For Claude Code** — run in your project:\n```bash\nclaude mcp add-json databricks '{\"command\":\"/path/to/databricks-exec-code-mcp/.venv/bin/python\",\"args\":[\"/path/to/databricks-exec-code-mcp/mcp_tools/tools.py\"]}'\n```\n\n\u003e Replace `/path/to/databricks-exec-code-mcp` with the actual path from Step 1.\n\n#### Step 5: Start Prompting!\n\n\u003e 💡 **Smart Cluster Selection**: If no `cluster_id` is provided, the MCP server automatically finds a running cluster in your workspace.\n\nJust describe what you want in natural language:\n\n**Data Engineering:**\n\u003e \"Build a Data Engineering pipeline using Medallion Architecture on the NYC Taxi dataset and deploy it with DABs\"\n\n**Machine Learning:**\n\u003e \"Train a classification model on the Titanic dataset, register it to Unity Catalog, and deploy as a DAB job\"\n\n**Quick Test:**\n\u003e \"Run a SQL query to show the top 10 tables in my catalog\"\n\n---\n\n### 📁 What Gets Generated\n\nThe AI will create a complete DABs project:\n\n```\nyour-project/\n├── databricks.yml              # DABs configuration\n├── resources/\n│   └── training_job.yml        # Databricks job definition\n├── src/\u003cproject\u003e/\n│   └── notebooks/\n│       ├── 01_data_prep.py\n│       ├── 02_training.py\n│       └── 03_validation.py\n└── tests/                      # Unit tests (optional)\n```\n\n---\n\n### 🌟 Features\n\n| Feature | Description |\n|---------|-------------|\n| **Direct Cluster Execution** | Test code on Databricks clusters via Databricks Execution API|\n| **DABs Packaging** | Production-ready bundle deployment |\n| **Multi-Environment** | Support for dev/staging/prod targets |\n| **Unity Catalog** | Models and data registered to UC for governance |\n| **MLflow Tracking** | Experiment tracking and model versioning |\n\n---\n\n### 📚 Resources\n\n- [Databricks Asset Bundles](https://docs.databricks.com/dev-tools/bundles/index.html)\n- [MLOps Deployment Patterns](https://docs.databricks.com/aws/en/machine-learning/mlops/deployment-patterns)\n- [MCP Specification](https://modelcontextprotocol.io/)\n- [SKILLS](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview)\n\n---\n\n### 📜 License\n\n© 2025 Databricks, Inc. All rights reserved. The source in this project is provided subject to the [Databricks License](LICENSE.md).\n\n#### Third-Party Licenses\n\n| Package | License | Copyright |\n|---------|---------|-----------|\n| [mcp](https://github.com/modelcontextprotocol/python-sdk) | MIT License | Copyright (c) 2024 Anthropic |\n| [requests](https://github.com/psf/requests) | Apache License 2.0 | Copyright 2019 Kenneth Reitz |\n| [python-dotenv](https://github.com/theskumar/python-dotenv) | BSD 3-Clause License | Copyright (c) 2014, Saurabh Kumar |\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatabricks-solutions%2Fdatabricks-exec-code-mcp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdatabricks-solutions%2Fdatabricks-exec-code-mcp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdatabricks-solutions%2Fdatabricks-exec-code-mcp/lists"}