streamble-http -client

This MCP client serves as an interactive conversational interface that leverages Azure OpenAI to understand user queries and route them to the Food Recipe MCP server tools. The client can list all recipes, search recipes by ingredients, and search recipes by name, presenting the results in a user-friendly, readable format. The integrated MCP tools at work are: get_recipes (list all recipes), search_recipe_by_ingredients (find recipes based on provided ingredients), and get_recipe_by_name (locate a recipe by its name). Connect to your MCP server URL via the FOOD_MCP_SERVER_URL environment variable, and ensure your Azure OpenAI credentials are correctly configured for the best results.

Prerequisites:

• Python 3.8+
• pip (comes with Python 3.8+)
• Access to a running Food Recipe MCP server
• Azure OpenAI resources (API key, endpoint, deployment)

Installation steps:

1. Clone the repository or download the project files.
2. Create and activate a Python virtual environment (optional but recommended):

python -m venv venv
# Windows
venv\Scripts\activate
# macOS/Linux
source venv/bin/activate

3. Install dependencies:

pip install -r requirements.txt

4. Create a .env file in the project root with the required environment variables (see the example below).
5. Run the client:

python foodRecipeClient.py

Notes:

• Ensure the MCP server is reachable at the configured FOOD_MCP_SERVER_URL.
• Update AZURE_OPENAI_* variables to match your Azure OpenAI resource settings.

Environment variables:

• AZURE_OPENAI_API_KEY: Your Azure OpenAI API key
• AZURE_OPENAI_ENDPOINT: Your Azure OpenAI endpoint URL
• AZURE_OPENAI_DEPLOYMENT_NAME: Deployment name for the model
• AZURE_OPENAI_API_VERSION: API version (e.g., 2024-02-15-preview)
• FOOD_MCP_SERVER_URL: URL of your Food Recipe MCP server

Common issues:

• Incorrect API keys or endpoint causing authentication errors with Azure OpenAI.
• MCP server URL unreachable due to network or server downtime.
• Dependency mismatches; ensure requirements.txt is installed in a compatible Python environment.

Tips:

• Validate MCP server tools are enabled and accessible (get_recipes, search_recipe_by_ingredients, get_recipe_by_name).
• Use descriptive prompts to guide the AI toward using the MCP tools for accurate results.