MCP Client

System requirements

• Python 3.10 or higher installed.
• You must use the Python MCP SDK 1.2.0 or higher.

Set up your environment

First, let’s install uv and set up our Python project and environment:

MacOS/Linux

curl -LsSf https://astral.sh/uv/install.sh | sh

Windows

powershell -ExecutionPolicy ByPass -c "irm https://astral.sh/uv/install.ps1 | iex"

Clone the repository

git clone git@github.com:digital-ai/mcp-client.git

cd mcp-client

Create virtual environment and activate it

MacOS/Linux

uv venv
source .venv/bin/activate

Windows

uv venv
.venv\Scripts\activate

Install dependencies

uv add -r requirements.txt

Add .env file

The .env file is used to set environment variables for your application. It is not included in the repository for security reasons. You can create it by copying the .env.sample file provided in the repository.

cp .env.sample .env

Then, open the .env file and set the required environment variables.

Add .mcp_server_config.json file

The .mcp_server_config.json file is used to set the configuration for your MCP server. It is not included in the repository for security reasons. You can create it by copying the .mcp_server_config.json.sample file provided in the repository.

cp .mcp_server_config.json.sample .mcp_server_config.json

Then, open the .mcp_server_config.json file and set the required configuration.

Running Backend Service

Run the backend service using the following command:

uvicorn multi_server_mcp_client:app:app --host 0.0.0.0 --port 8003 --reload

Backend URL: http://localhost:8003/

Running Frontend Streamlit App

Run the frontend Streamlit app using the following command:

streamlit run streamlit_chat.py --server.port 8501 --server.address 0.0.0.0

Application URL: http://localhost:8501/