### Setup Python Virtual Environment and Install Dependencies

Source: https://github.com/arjunprabhulal/adk-python-mcp-client/blob/main/README.md

This snippet provides commands to set up a Python virtual environment, activate it, and install necessary dependencies like `google-adk`, `mcp-flight-search`, `google-generativeai`, and `python-dotenv`. It also shows how to set required environment variables for Google API key and SerpAPI key.

```bash
# Setup virtual environment (Mac or Unix)
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install dependencies
pip install google-adk  # Agent Development Kit
pip install mcp-flight-search  # MCP server 
pip install google-generativeai python-dotenv  # GenAI Python SDK

# Note: ADK uses GOOGLE_API_KEY instead of GEMINI_API_KEY
export GOOGLE_API_KEY="your-google-api-key"
export SERP_API_KEY="your-serpapi-key"
```

--------------------------------

### Set Up Python Virtual Environment and Dependencies

Source: https://github.com/arjunprabhulal/adk-python-mcp-client/blob/main/README.md

Commands to create and activate a Python virtual environment, then install all required project dependencies listed in `requirements.txt` using pip. Includes notes for Windows users.

```bash
# Setup virtual environment (Mac or Unix)
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate

# Install all dependencies from requirements.txt
pip install -r requirements.txt
```

--------------------------------

### Configure Environment Variables

Source: https://github.com/arjunprabhulal/adk-python-mcp-client/blob/main/README.md

Steps to copy the example environment file (`.env.example`) to `.env` and then edit it to add actual API keys for services like Google API and SerpAPI, which are necessary for the application to function.

```bash
# Copy the example environment file
cp .env.example .env

# Edit the .env file with your actual API keys
# Replace placeholders with your actual keys:
# GOOGLE_API_KEY=your-actual-google-api-key
# SERP_API_KEY=your-actual-serpapi-key
```

--------------------------------

### Example User Query for Flight Search

Source: https://github.com/arjunprabhulal/adk-python-mcp-client/blob/main/README.md

This snippet provides an example of a user query string used to demonstrate the flight search assistant's capabilities. It shows the typical input format for a flight search request.

```text
"Find flights from Atlanta to Las Vegas 2025-05-05"
```

--------------------------------

### Start ADK Client Application

Source: https://github.com/arjunprabhulal/adk-python-mcp-client/blob/main/README.md

Command to run the main client script (`client.py`), which initiates the application. This process involves connecting to the MCP Flight Search server, initializing the ADK agent, and processing queries.

```bash
python client.py
```

--------------------------------

### Verify MCP Flight Search Server Installation

Source: https://github.com/arjunprabhulal/adk-python-mcp-client/blob/main/README.md

This command verifies that the `mcp-flight-search` server is correctly installed in the Python environment, displaying its package information.

```bash
pip show mcp-flight-search
```

--------------------------------

### Connect to MCP Flight Search Server and Get Tools

Source: https://github.com/arjunprabhulal/adk-python-mcp-client/blob/main/README.md

This asynchronous Python function `get_tools_async` connects to the `mcp-flight-search` server using `StdioServerParameters`. It retrieves the available tools from the server, which are then used by the ADK agent. It also manages the server's lifecycle with an exit stack.

```python
# --- Step 1: Get tools from MCP server ---
async def get_tools_async():
    """Gets tools from the Flight Search MCP Server."""
    print("Attempting to connect to MCP Flight Search server...")
    server_params = StdioServerParameters(
        command="mcp-flight-search",
        args=["--connection_type", "stdio"],
        env={"SERP_API_KEY": os.getenv("SERP_API_KEY")},
    )
    
    tools, exit_stack = await MCPToolset.from_server(
        connection_params=server_params
    )
    print("MCP Toolset created successfully.")
    return tools, exit_stack
```

--------------------------------

### Initialize ADK Runner and Session

Source: https://github.com/arjunprabhulal/adk-python-mcp-client/blob/main/README.md

This Python snippet demonstrates how to initialize an in-memory session service, create a new session, define a user query, format it as `types.Content`, and set up the ADK `Runner` with the agent and session service. It prepares the environment for executing an ADK agent.

```python
async def async_main():
    # Create services
    session_service = InMemorySessionService()
  
    # Create a session
    session = session_service.create_session(
        state={}, app_name='flight_search_app', user_id='user_flights'
    )
  
    # Define the user prompt
    query = "Find flights from Atlanta to Las Vegas 2025-05-05"
    print(f"User Query: '{query}'")
    
    # Format input as types.Content
    content = types.Content(role='user', parts=[types.Part(text=query)])
  
    # Get agent and exit_stack
    root_agent, exit_stack = await get_agent_async()
  
    # Create Runner
    runner = Runner(
        app_name='flight_search_app',
        agent=root_agent,
        session_service=session_service,
    )
```

--------------------------------

### Clone ADK Python MCP Client Repository

Source: https://github.com/arjunprabhulal/adk-python-mcp-client/blob/main/README.md

Instructions to clone the project repository from GitHub and navigate into the project directory using standard Git and Bash commands.

```bash
git clone https://github.com/arjunprabhulal/adk-python-mcp-client.git
cd adk-python-mcp-client
```

--------------------------------

### ADK Python MCP Client Project Directory Structure

Source: https://github.com/arjunprabhulal/adk-python-mcp-client/blob/main/README.md

An overview of the project's file and directory layout, detailing the purpose of key files and folders such as `Images/`, `client.py`, `README.md`, `requirements.txt`, and environment variable files.

```text
adk-python-mcp-client/
├── Images/
│   ├── adk-mcp-client-log.gif      # Standard logging demo animation
│   ├── adk-mcp-client-debug.gif    # Debug mode demo animation
│   └── image.png                   # Architecture diagram
├── client.py                       # ADK client implementation
├── README.md                       # Project documentation
├── requirements.txt                # Dependencies
├── .env.example                    # Environment variables template
└── .env                            # Environment variables (not tracked by Git)
```

--------------------------------

### Create ADK LlmAgent with MCP Server Tools

Source: https://github.com/arjunprabhulal/adk-python-mcp-client/blob/main/README.md

This asynchronous Python function `get_agent_async` creates an `LlmAgent` instance, equipping it with the tools fetched from the MCP server. It configures the agent with a specific Gemini model, a name, and an instruction for flight search tasks, handling one-way trips by using an empty string for the return date.

```python
# --- Step 2: Define ADK Agent Creation ---
async def get_agent_async():
    """Creates an ADK Agent equipped with tools from the MCP Server."""
    tools, exit_stack = await get_tools_async()
    print(f"Fetched {len(tools)} tools from MCP server.")
    
    # Create the LlmAgent
    root_agent = LlmAgent(
        model=os.getenv("GEMINI_MODEL", "gemini-2.5-pro-preview-03-25"),
        name='flight_search_assistant',
        instruction='Help user to search for flights using available tools based on prompt. If return date not specified, use an empty string for one-way trips.',
        tools=tools,
    )
    
    return root_agent, exit_stack
```

--------------------------------

### Execute ADK Agent and Process Events

Source: https://github.com/arjunprabhulal/adk-python-mcp-client/blob/main/README.md

This Python code shows how to execute the ADK `Runner` asynchronously with a new message. It then iterates through the received events and ensures proper cleanup of resources, such as closing the MCP server connection using an `exit_stack`.

```python
    print("Running agent...")
    events_async = runner.run_async(
        session_id=session.id,
        user_id=session.user_id,
        new_message=content
    )
  
    # Process events
    async for event in events_async:
        print(f"Event received: {event}")
  
    # Always clean up resources
    print("Closing MCP server connection...")
    await exit_stack.aclose()
    print("Cleanup complete.")
```

=== COMPLETE CONTENT === This response contains all available snippets from this library. No additional content exists. Do not make further requests.