Hickey_MCP
Personal MCP server for Snowflake and Tableau integration, enabling SQL queries and database/table listing as well as Tableau workbook, view, datasource management.
README
Hickey_MCP
Personal MCP (Model Context Protocol) server built with FastMCP for Tableau and Snowflake integration.
Features
Snowflake Tools
- execute_snowflake_query: Execute SQL queries and retrieve results
- list_snowflake_databases: List all available databases
- list_snowflake_tables: List tables in a specific database and schema
Tableau Tools
- list_tableau_workbooks: List all workbooks on Tableau Server
- get_tableau_workbook_views: Get all views in a specific workbook
- list_tableau_datasources: List all datasources on Tableau Server
- refresh_tableau_datasource: Trigger a refresh of a datasource
Setup
1. Clone the repository
git clone https://github.com/YOUR_USERNAME/Hickey_MCP.git
cd Hickey_MCP
2. Create virtual environment
python -m venv venv
source venv/bin/activate # On Windows: venv\Scripts\activate
3. Install dependencies
pip install -r requirements.txt
4. Configure environment variables
Copy .env.example to .env and fill in your credentials:
cp .env.example .env
Edit .env with your actual credentials:
- Snowflake account, user, password, warehouse, database, and schema
- Tableau server URL, username, password, and site ID
5. Run the server
python hickey_mcp_server.py
Usage with Claude Desktop
Add this configuration to your Claude Desktop config file:
MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"hickey-mcp": {
"command": "python",
"args": ["C:/Users/kylec/OneDrive - CHG Healthcare/Hickey_MCP/hickey_mcp_server.py"]
}
}
}
Restart Claude Desktop after adding this configuration.
Security Notes
- Never commit your
.envfile or any credentials to the repository - The
.gitignorefile is configured to exclude sensitive files - Keep your Snowflake and Tableau credentials secure
- This is a personal server - do not share credentials or expose the server publicly
Example Queries
Once connected, you can ask Claude to:
- "List all databases in Snowflake"
- "Show me the tables in the ANALYTICS schema"
- "Execute this query on Snowflake: SELECT * FROM customers LIMIT 10"
- "List all Tableau workbooks"
- "Get the views from workbook ID xyz123"
- "Refresh datasource abc456"
Development
To add more tools, use the @mcp.tool() decorator in hickey_mcp_server.py:
@mcp.tool()
def your_new_tool(param: str) -> str:
"""
Tool description
Args:
param: Parameter description
Returns:
Return value description
"""
# Your implementation
pass
License
Personal use only.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。