Mage.ai MCP Integration

Mage.ai MCP 集成

一个全面的 Mage.ai 模型上下文协议（MCP）集成，让 Anthropic 的 Claude 等 AI 助手能够高效地处理 Mage 数据流水线。

功能

• 浏览流水线：探索所有 Mage.ai 流水线及其组件
• 查看和编辑代码：读取和修改区块代码
• 执行流水线：运行整个流水线或单个区块
• 搜索功能：按名称、类型或内容查找区块
• 创建流水线：从头创建新流水线和区块

安装

# Clone the repository
git clone https://github.com/yourusername/mage-mcp.git
cd mage-mcp

# Install dependencies
pip install -r requirements.txt

配置

可以通过环境变量或命令行参数配置服务：

• MAGE_API_URL：Mage.ai API 的 URL（默认值：http://localhost:6789/api/）
• MAGE_API_KEY：用于身份验证的 API 密钥（如有要求）

创建 .env 文件以保存持久配置：

MAGE_API_URL=http://localhost:6789/api/
MAGE_API_KEY=your_api_key_if_needed

使用方法

运行服务

使用提供的脚本启动 MCP 服务：

# Using stdio transport (default)
python run_server.py

# Using SSE transport
python run_server.py --transport sse --host localhost --port 3000

# Additional options
python run_server.py --api-url http://your-mage-instance:6789/api/ --api-key your_key --debug

使用 Claude Desktop 安装

为获得最佳体验，请直接通过 Claude Desktop 安装此服务：

# Using mcp CLI
mcp install run_server.py --name "Mage.ai Manager"

# With environment variables
mcp install run_server.py -v MAGE_API_URL=http://localhost:6789/api/ -v MAGE_API_KEY=your_key

开发模式

用于测试和开发：

mcp dev run_server.py

MCP 资源和工具

资源

• mage://pipelines - 列出所有流水线
• mage://pipelines/{pipeline_uuid} - 获取流水线详情
• mage://pipelines/{pipeline_uuid}/blocks - 列出流水线中的区块
• mage://pipelines/{pipeline_uuid}/blocks/{block_uuid} - 获取区块详情
• mage://pipelines/{pipeline_uuid}/blocks/{block_uuid}/content - 获取区块代码
• mage://pipelines/{pipeline_uuid}/content - 获取整个流水线的内容
• mage://pipelines/{pipeline_uuid}/execution - 获取流水线执行详情
• mage://blocks/search/{query} - 按名称、类型或内容搜索区块

工具

• list_all_pipelines() - 列出所有流水线及其详情
• get_pipeline_details(pipeline_uuid) - 获取流水线信息
• list_pipeline_blocks(pipeline_uuid) - 列出流水线中的区块
• get_block_content(pipeline_uuid, block_uuid) - 获取区块代码
• create_pipeline(name, description, pipeline_type) - 创建新流水线
• create_block(pipeline_uuid, name, block_type, language, content, upstream_blocks) - 创建区块
• update_block_content(pipeline_uuid, block_uuid, content) - 更新区块代码
• execute_pipeline(pipeline_uuid) - 运行流水线
• execute_block(pipeline_uuid, block_uuid) - 运行指定区块
• get_pipeline_code(pipeline_uuid) - 获取完整的流水线代码

交互示例

User: Show me all the pipelines in Mage.ai.
Claude: Let me check what pipelines are available in your Mage.ai instance.

[Lists all pipelines with descriptions and types]

User: Can you show me the blocks in the data_ingestion pipeline?
Claude: Here are all the blocks in the data_ingestion pipeline:

[Lists all blocks with their types, languages, and status]

User: I need to modify the 'transform_data' block to fix a bug.
Claude: Let me help you with that. First, let's look at the current code:

[Shows the current block code]

Here's how we can fix the bug:
[Explains the issue and suggests changes]

Would you like me to update the block with these changes?

User: Yes, please update it.
Claude: I've updated the block. Here's the new content:

[Shows the updated code]

The changes have been saved successfully.

参与贡献

欢迎贡献！请随时提交 Pull Request。

许可证

本项目采用 MIT 许可证，详情请参阅 LICENSE 文件。