Databricks MCP 060ce45c

MCPAI代理

提供方 THEAVINASHREDDY

AI代理 stdio · 本地进程 Token 社区 / 第三方 ClaudeCursor
查看接入方式

Databricks MCP 服务器是一个实现 MCP 协议的服务,允许 LLMs 与 Databricks 交互,提供集群管理、作业管理、工作区文件操作等功能。

一句话选型结论

按资料字段整理

Databricks MCP 060ce45c 属于AI代理类 MCP 服务器,stdio · 本地进程,Token,可直接接入 Claude、Cursor,有可直接执行的安装命令。接入前先确认权限范围;涉及写入、删除或付款的操作,建议先在测试环境验证。

分类AI代理 传输方式stdio · 本地进程 鉴权Token 部署方式本地部署
GitHub 星标 0 仓库热度,无公开仓库时显示未标注
工具数 38 暴露给模型的工具数量
资源 / 提示词 0 / 0 资源与提示词模板数量
维护方 社区 / 第三方 核验等级 仅资料核对

工具与能力

AI代理
数量来自来源目录的标注,具体工具清单以官方文档为准
工具数量38暴露给模型可调用的工具个数
资源数量0可读取的资源条目
提示词数量0内置提示词模板数量

能力标签

支持客户端

适用场景

MCP协议Python本地部署Databricks集成集群管理作业调度工作区文件操作

安装与配置

stdio · 本地进程 Token
客户端在本机拉起子进程,数据不出本机
pip install -e .

这条命令只是入口,具体启动参数请按官方文档补齐,不要直接照搬到别的服务器。

  1. 1
    准备运行环境

    stdio 服务在本地起进程,需要先装好 Node.js 等运行时,再按安装命令拉取依赖。

  2. 2
    安装服务

    复制上面的安装命令执行;命令里带占位符的位置,换成自己的密钥或路径。

  3. 3
    写入客户端配置

    在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,让新配置生效。

  4. 4
    验证是否可用

    连接成功后客户端会列出约 38 个工具,随便调一个只读工具确认能返回结果。

典型使用场景

3 类
按分类与标签整理的常见用法,具体以官方文档为准
给代理接外部能力

让代理在任务中途调用搜索、数据库等真实工具。

多步任务编排

把一串操作拆成步骤,由代理按顺序执行。

自动化重复流程

把固定流程交给代理跑,减少手工操作。

选择建议

选之前先看这几条
按条目字段给出的判断,不替你决定用不用

值得选的地方

  • 资料标注 38 个工具,覆盖面较广,能满足多种调用。
  • 有现成的安装命令,不用自己找入口,照着跑就能起服务。
  • 已适配 Claude、Cursor,换客户端不用重新研究配置。

先想清楚的地方

  • stdio 方式要求本地装好运行时(如 Node.js),换机器要重新装一遍。
  • 使用前要准备好Token对应的凭据,并按最小权限配置。
  • 版本更新与行为细节以官方仓库为准。

更适合

  • 需要在AI代理场景里让模型直接调用外部能力的人。
  • 已经在用 Claude、Cursor 的用户,接入路径最短。
  • 想先快速试一下、能接受在本地或自有环境跑服务的人。

不太适合

  • 完全不想在本地装环境的人。
  • 不方便管理密钥或第三方授权的人。
  • 需要厂商级 SLA 和技术支持的生产环境。

同类对比

6 个同类
同分类里挑最接近的几条,字段以各自详情页为准
MCP 服务器工具数传输方式部署方式安装命令最后核验
Databricks MCP 060ce45c当前 38 stdio · 本地进程 本地部署 有 2026-05-17
Filesystem 560c4363 13 未标注 本地部署 无 2026-05-17
Server Everything (everything) 11 stdio · 本地进程 本地部署 有 2026-05-17
Time 7365cb6d 2 SSE · 服务端推送 远程部署 有 2026-05-18
Everything Claude Code 未标注 stdio · 本地进程 本地部署 有 2026-05-17
Openmemory 557e1585 未标注 stdio · 本地进程 本地部署 有 2026-05-17

服务器档案

AI代理
字段来自项目仓库与公开索引,中文说明由本站标注
提供方THEAVINASHREDDY上游标注的维护方 THEAVINASHREDDY
分类AI代理本站按上游分类展示
连接方式stdio · 本地进程客户端在本机拉起子进程,数据不出本机
鉴权方式Token远程服务建议用最小权限凭据
维护方社区 / 第三方核验等级 仅资料核对
包名 / 运行时未标注 · 未标注本地安装时用到的包标识与运行时
部署类型本地部署上游给出的部署形态
最近核验2026-05-17上游最后核验时间

详细介绍

15.4 KB
来自项目仓库与上游目录的原文,未做删改

Features

  • MCP Protocol Support: Implements the MCP protocol to allow LLMs to interact with Databricks
  • Databricks API Integration: Provides access to Databricks REST API functionality
  • Tool Registration: Exposes Databricks functionality as MCP tools
  • Async Support: Built with asyncio for efficient operation

Available Tools

The Databricks MCP Server exposes the following tools:

Cluster Management

  • list_clusters: List all Databricks clusters
  • create_cluster: Create a new Databricks cluster
  • terminate_cluster: Terminate a Databricks cluster
  • get_cluster: Get information about a specific Databricks cluster
  • start_cluster: Start a terminated Databricks cluster

Job Management

  • list_jobs: List all Databricks jobs
  • run_job: Run a Databricks job
  • run_notebook: Submit and wait for a one-time notebook run
  • create_job: Create a new Databricks job
  • delete_job: Delete a Databricks job
  • get_run_status: Get status information for a job run
  • list_job_runs: List recent runs for a job
  • cancel_run: Cancel a running job

Workspace Files

  • list_notebooks: List notebooks in a workspace directory
  • export_notebook: Export a notebook from the workspace
  • import_notebook: Import a notebook into the workspace
  • delete_workspace_object: Delete a notebook or directory
  • get_workspace_file_content: Retrieve content of any workspace file (JSON, notebooks, scripts, etc.)
  • get_workspace_file_info: Get metadata about workspace files

File System

  • list_files: List files and directories in a DBFS path
  • dbfs_put: Upload a small file to DBFS
  • dbfs_delete: Delete a DBFS file or directory

Cluster Libraries

  • install_library: Install libraries on a cluster
  • uninstall_library: Remove libraries from a cluster
  • list_cluster_libraries: Check installed libraries on a cluster

Repos

  • create_repo: Clone a Git repository
  • update_repo: Update an existing repo
  • list_repos: List repos in the workspace
  • pull_repo: Pull the latest commit for a Databricks repo

Unity Catalog

  • list_catalogs: List catalogs
  • create_catalog: Create a catalog
  • list_schemas: List schemas in a catalog
  • create_schema: Create a schema
  • list_tables: List tables in a schema
  • create_table: Execute a CREATE TABLE statement
  • get_table_lineage: Fetch lineage information for a table

Composite

  • sync_repo_and_run_notebook: Pull a repo and execute a notebook in one call

SQL Execution

  • execute_sql: Execute a SQL statement (warehouse_id optional if DATABRICKS_WAREHOUSE_ID env var is set)

🎉 Recent Updates (v0.3.0)

New Features - Repo Sync & Notebook Execution:
- ✅ Repository Management: Pull latest commits from Databricks repos with pull_repo tool
- ✅ One-time Notebook Execution: Submit and wait for notebook runs with run_notebook tool
- ✅ Composite Operations: Combined repo sync + notebook execution with sync_repo_and_run_notebook tool
- ✅ Enhanced Job Management: Extended job APIs with submit, status checking, and run management
- ✅ Comprehensive Testing: Full test coverage for all new functionality

Bug Fixes:
- ✅ Issue #9 Fixed: Resolved "Missing required parameter 'params'" error in Cursor and other MCP clients
- ✅ Parameter Handling: All MCP tools now correctly handle both nested and flat parameter structures
- ✅ Cursor Compatibility: Full compatibility with Cursor's MCP implementation

Previous Updates:
- v0.2.1: Enhanced Codespaces support, documentation improvements, publishing process streamlining
- v0.2.0: Major package refactoring from src/ to databricks_mcp/ structure

Backwards Compatibility: All existing MCP tools continue to work unchanged. New features extend functionality without breaking changes.

Installation

You'll need to set these environment variables:

  • DATABRICKS_HOST - Your Databricks workspace URL
  • DATABRICKS_TOKEN - Your Databricks personal access token
  • DATABRICKS_WAREHOUSE_ID - (Optional) Your default SQL warehouse ID

🔧 Local Installation (Development & Latest Features)

Want to use the latest bug fixes and features? Install from source for development or to get the most recent improvements.

👉 Quick Start Guide → | Detailed Instructions →

Quick Local Setup```bash

1. Clone the repository

git clone https://github.com/THEAVINASHREDDY/databricks-mcp.git
cd databricks-mcp

2. Install in editable mode

pip install -e .

3. Configure mcp.json with your credentials + PYTHONPATH


**Benefits of Local Installation:**
- ✅ Get latest bug fixes immediately (see FIXES_SUMMARY.md)
- ✅ Code changes take effect instantly (editable install)
- ✅ Full control over the installation
- ✅ Easy to contribute improvements back

**Configuration for Local Install:**

Update your `~/.cursor/mcp.json`:```json
{
  "mcpServers": {
    "databricks-mcp": {
      "command": "python",
      "args": ["-m", "databricks_mcp.server.databricks_mcp_server"],
      "env": {
        "DATABRICKS_HOST": "https://your-workspace.databricks.com",
        "DATABRICKS_TOKEN": "dapiXXXXXXXXXXXXXXXXXXXXXXXXXXXX",
        "DATABRICKS_WAREHOUSE_ID": "sql_warehouse_xxxxx",
        "PYTHONPATH": "/absolute/path/to/databricks-mcp"
      }
    }
  }
}

Documentation:
- 🚀 QUICKSTART.md - Get started in 5 minutes
- 📦 INSTALLATION.md - Detailed platform-specific instructions
- 🔧 TROUBLESHOOTING.md - Common issues and solutions
- 🐛 FIXES_SUMMARY.md - Latest bug fixes and improvements

Manual Installation

Prerequisites

  • Python 3.10 or higher
  • uv package manager (recommended for MCP servers)

The setup script will:
- Install uv if not already installed
- Create a virtual environment
- Install all project dependencies
- Verify the installation works

Running the MCP Server

Standalone

To start the MCP server directly for testing or development, run:```bash

Activate your virtual environment if not already active

source .venv/bin/activate

Run the start script (handles finding env vars from .env if needed)

./scripts/start_mcp_server.sh


This is useful for seeing direct output and logs.

### Integrating with AI Clients

To use this server with AI clients like Cursor or Claude CLI, you need to register it.

#### Cursor Setup

1.  Open your global MCP configuration file located at `~/.cursor/mcp.json` (create it if it doesn't exist).
2.  Add the following entry within the `mcpServers` object, replacing placeholders with your actual values and ensuring the path to `start_mcp_server.sh` is correct:```json
    {
      "mcpServers": {
        // ... other servers ...
        "databricks-mcp-local": {
          "command": "/absolute/path/to/your/project/databricks-mcp-server/start_mcp_server.sh",
          "args": [],
          "env": {
            "DATABRICKS_HOST": "https://your-databricks-instance.azuredatabricks.net",
            "DATABRICKS_TOKEN": "dapiXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX",
            "DATABRICKS_WAREHOUSE_ID": "sql_warehouse_12345",
            "RUNNING_VIA_CURSOR_MCP": "true"
          }
        }
        // ... other servers ...
      }
    }
    ```

3.  **Important:** Replace `/absolute/path/to/your/project/databricks-mcp-server/` with the actual absolute path to this project directory on your machine.
4.  Replace the `DATABRICKS_HOST` and `DATABRICKS_TOKEN` values with your credentials.
5.  Save the file and **restart Cursor**.

6.  You can now invoke tools using `databricks-mcp-local:` (e.g., `databricks-mcp-local:list_jobs`).

#### Claude CLI Setup

1.  Use the `claude mcp add` command to register the server. Provide your credentials using the `-e` flag for environment variables and point the command to the `start_mcp_server.sh` script using `--` followed by the absolute path:```bash
    claude mcp add databricks-mcp-local \
      -s user \
      -e DATABRICKS_HOST="https://your-databricks-instance.azuredatabricks.net" \
      -e DATABRICKS_TOKEN="dapiXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXXX" \
      -e DATABRICKS_WAREHOUSE_ID="sql_warehouse_12345" \
      -- /absolute/path/to/your/project/databricks-mcp-server/start_mcp_server.sh
    ```

2.  **Important:** Replace `/absolute/path/to/your/project/databricks-mcp-server/` with the actual absolute path to this project directory on your machine.
3.  Replace the `DATABRICKS_HOST` and `DATABRICKS_TOKEN` values with your credentials.

4.  You can now invoke tools using `databricks-mcp-local:` in your Claude interactions.

## Querying Databricks Resources

The repository includes utility scripts to quickly view Databricks resources:```bash
# View all clusters
uv run scripts/show_clusters.py

# View all notebooks
uv run scripts/show_notebooks.py

Usage Examples

SQL Execution with Default Warehouse```python

With DATABRICKS_WAREHOUSE_ID set, warehouse_id is optional

await session.call_tool("execute_sql", {
"statement": "SELECT * FROM my_table LIMIT 10"
})

You can still override the default warehouse

await session.call_tool("execute_sql", {
"statement": "SELECT * FROM my_table LIMIT 10",
"warehouse_id": "sql_warehouse_specific"
})


### Workspace File Content Retrieval```python
# Get JSON file content from workspace
await session.call_tool("get_workspace_file_content", {
    "workspace_path": "/Users/user@domain.com/config/settings.json"
})

# Get notebook content in Jupyter format
await session.call_tool("get_workspace_file_content", {
    "workspace_path": "/Users/user@domain.com/my_notebook",
    "format": "JUPYTER"
})

# Get file metadata without downloading content
await session.call_tool("get_workspace_file_info", {
    "workspace_path": "/Users/user@domain.com/large_file.py"
})

Repo Sync and Notebook Execution```python

await session.call_tool("sync_repo_and_run_notebook", {
"repo_id": 123,
"notebook_path": "/Repos/user/project/run_me"
})


### Create Nightly ETL Job```python
job_conf = {
    "name": "Nightly ETL",
    "tasks": [
        {
            "task_key": "etl",
            "notebook_task": {"notebook_path": "/Repos/me/etl.py"},
            "existing_cluster_id": "abc-123"
        }
    ]
}
await session.call_tool("create_job", job_conf)

Project Structure```

databricks-mcp/
├── databricks_mcp/ # Main package (renamed from src/)
│ ├── init.py # Package initialization
│ ├── main.py # Main entry point for the package
│ ├── main.py # Entry point for the MCP server
│ ├── api/ # Databricks API clients
│ │ ├── clusters.py # Cluster management
│ │ ├── jobs.py # Job management
│ │ ├── notebooks.py # Notebook operations
│ │ ├── sql.py # SQL execution
│ │ └── dbfs.py # DBFS operations
│ ├── core/ # Core functionality
│ │ ├── config.py # Configuration management
│ │ ├── auth.py # Authentication
│ │ └── utils.py # Utilities
│ ├── server/ # Server implementation
│ │ ├── main.py # Server entry point
│ │ ├── databricks_mcp_server.py # Main MCP server
│ │ └── app.py # FastAPI app for tests
│ └── cli/ # Command-line interface
│ └── commands.py # CLI commands
├── tests/ # Test directory
│ ├── test_clusters.py # Cluster tests
│ ├── test_mcp_server.py # Server tests
│ └── test_*.py # Other test files
├── scripts/ # Helper scripts (organized)
│ ├── start_mcp_server.ps1 # Server startup script (Windows)
│ ├── start_mcp_server.sh # Server startup script (Unix)
│ ├── run_tests.ps1 # Test runner script (Windows)
│ ├── run_tests.sh # Test runner script (Unix)
│ ├── setup.ps1 # Setup script (Windows)
│ ├── setup.sh # Setup script (Unix)
│ ├── show_clusters.py # Script to show clusters
│ ├── show_notebooks.py # Script to show notebooks
│ ├── setup_codespaces.sh # Codespaces setup
│ └── test_setup_local.sh # Local test setup
├── examples/ # Example usage
│ ├── direct_usage.py # Direct usage examples
│ └── mcp_client_usage.py # MCP client examples
├── docs/ # Documentation (organized)
│ ├── AGENTS.md # Agent documentation
│ ├── project_structure.md # Detailed structure docs
│ ├── new_features.md # Feature documentation
│ └── phase1.md # Development phases
├── .gitignore # Git ignore rules
├── .cursor.json # Cursor configuration
├── pyproject.toml # Package configuration
├── uv.lock # Dependency lock file
└── README.md # This file


See `docs/project_structure.md` for a more detailed view of the project structure.

## Development

### Code Standards

- Python code follows PEP 8 style guide with a maximum line length of 100 characters
- Use 4 spaces for indentation (no tabs)
- Use double quotes for strings
- All classes, methods, and functions should have Google-style docstrings
- Type hints are required for all code except tests

### Linting

The project uses the following linting tools:```bash
# Run all linters
uv run pylint databricks_mcp/ tests/
uv run flake8 databricks_mcp/ tests/
uv run mypy databricks_mcp/

Testing

The project uses pytest for testing. To run the tests:```bash

Run all tests with our convenient script

.\scripts\run_tests.ps1

Run with coverage report

.\scripts\run_tests.ps1 -Coverage

Run specific tests with verbose output

.\scripts\run_tests.ps1 -Verbose -Coverage tests/test_clusters.py


You can also run the tests directly with pytest:```bash
# Run all tests
uv run pytest tests/

# Run with coverage report
uv run pytest --cov=databricks_mcp tests/ --cov-report=term-missing

A minimum code coverage of 80% is the goal for the project.

Documentation

  • API documentation is generated using Sphinx and can be found in the docs/api directory
  • All code includes Google-style docstrings
  • See the examples/ directory for usage examples

Examples

Check the examples/ directory for usage examples. To run examples:```bash

Run example scripts with uv

uv run examples/direct_usage.py
uv run examples/mcp_client_usage.py
```

Contributing

Contributions are welcome! Please feel free to submit a Pull Request.

  1. Ensure your code follows the project's coding standards
  2. Add tests for any new functionality
  3. Update documentation as necessary
  4. Verify all tests pass before submitting

License

This project is licensed under the MIT License - see the LICENSE file for details.

About

A Model Completion Protocol (MCP) server for interacting with Databricks services.

Credit for the initial version goes to @JustTryAI.

常见问题

8 问
答案由本站依据条目字段整理,不引用上游原文
Databricks MCP 060ce45c 怎么安装?

在客户端按下面的安装命令接入:pip install -e .。装完在客户端配置里引用同一个包或端点。

Databricks MCP 060ce45c 怎么在 Claude、Cursor 里配置?

它的传输方式是stdio · 本地进程,在客户端的 MCP 配置里填好启动命令和参数,保存后完全退出客户端再打开,配置才会生效。

Databricks MCP 060ce45c 收费吗?

本站不代收费用,也没有标注具体价格。是否收费取决于服务本身和背后的接口额度,正式使用前按官方说明确认。

Databricks MCP 060ce45c 需要 API Key 吗?

资料标注需要Token认证,使用前准备好对应凭据,并按最小权限配置。

Databricks MCP 060ce45c 支持哪些客户端?

资料标注支持 Claude、Cursor;其他客户端只要能配置 MCP Server,也能用同样的命令或地址接入。

Databricks MCP 060ce45c 能提供哪些能力?

资料显示约 38 个工具;能力标签包括 集群管理、Python、Claude。具体工具清单以官方文档为准。

Databricks MCP 060ce45c 需要什么运行环境?

属于本地进程,需要在本机装好运行环境。

Databricks MCP 060ce45c 是本地还是远程?

它是本地进程(stdio),由客户端在本机拉起。传输方式为stdio · 本地进程。

热门专题

按标签挑服务器
全部专题 →

服务器信息以作者仓库与官方文档为准;分类、传输方式与鉴权方式的中文说明为中文整理,最近核验 2026-05-17。