vivian-xie-db
MCP Servervivian-xie-dbpublic

mcp_client

提供命令行和基于 Dash 的 Web 客户端,用于与 MCP 工具交互,支持 Databricks 认证。

Repository Info

0
Stars
0
Forks
0
Watchers
0
Issues
Python
Language
-
License

About This Server

提供命令行和基于 Dash 的 Web 客户端,用于与 MCP 工具交互,支持 Databricks 认证。

Model Context Protocol (MCP) - This server can be integrated with AI applications to provide additional context and capabilities, enabling enhanced AI interactions and functionality.

Documentation

MCP Client

This project provides both a command-line and a web-based Dash client for interacting with an MCP tools, leveraging Databricks authentication and the fastmcp library. It allows users to list and call available tools from the MCP tools, either programmatically or through a user-friendly web interface.

Features

  • Command-line client (mcp_client.py):

    • Authenticates with Databricks.
    • Lists available tools from the MCP tools.
    • Calls a specified tool and prints the result.
  • Dash web client (mcp_dash_client.py):

    • Modern, responsive UI built with Dash and Bootstrap.
    • Connect to an MCP server endpoint with a Databricks token.
    • List available tools and dynamically render input forms for tool arguments.
    • View results interactively.

Install dependencies with:

pip install -r requirements.txt

Usage

Command-Line Client

Edit mcp_client.py to set the correct MCP server URL.

Run:

python mcp_client.py

This will:

  • Authenticate using your Databricks credentials.
  • List available tools.
  • Call the genie-query tool with a sample query.

Dash Web Client

Deploying to Databricks Apps

You can deploy the MCP Client Dash app as a Databricks app by following these steps:

  1. Clone the Repository to Your Workspace

    In your Databricks workspace, navigate to the directory where you want to deploy the app (e.g., /Workspace/Users/your.email@databricks.com/mcp_client). Then, clone the repository:

    git clone https://github.com/your-org/mcp_client.git
    
  2. Create and Deploy the App in Databricks

    • Go to the Databricks Apps interface.
    • Create a new app and specify the path to the directory where you cloned the repository.
    • Complete the app creation and deployment process.

    databricks apps deploy mcp-client --source-code-path /Workspace/Users/your.email@databricks.com/mcp_client

  3. Access the Dash App

    Once deployed, your MCP Client Dash app will be running and accessible via the configured port and endpoint. You can now interact with the MCP server through the web interface provided by the app, or use the command-line client as needed. Please note that in order to access the MCP server url deployed on Databricks apps, the url must look like https://app_url.aws.databricksapps.com/api/mcp/ with "/" added at the end

Quick Start

1

Clone the repository

git clone https://github.com/vivian-xie-db/mcp_client
2

Install dependencies

cd mcp_client
npm install
3

Follow the documentation

Check the repository's README.md file for specific installation and usage instructions.

Repository Details

Ownervivian-xie-db
Repomcp_client
LanguagePython
License-
Last fetched8/10/2025

Recommended MCP Servers

💬

Discord MCP

Enable AI assistants to seamlessly interact with Discord servers, channels, and messages.

integrationsdiscordchat
🔗

Knit MCP

Connect AI agents to 200+ SaaS applications and automate workflows.

integrationsautomationsaas
🕷️

Apify MCP Server

Deploy and interact with Apify actors for web scraping and data extraction.

apifycrawlerdata
🌐

BrowserStack MCP

BrowserStack MCP Server for automated testing across multiple browsers.

testingqabrowsers

Zapier MCP

A Zapier server that provides automation capabilities for various apps.

zapierautomation