Remote MCP Azure Function

🚀 AlphaVantage MCP Server with Azure Functions

This project implements an Azure Function that serves as a bridge between the proxy and the AlphaVantage financial API. It enables AI agents to access financial data and perform financial analysis via MCP.

The Azure Function exposes the following financial data endpoints as MCP tools:

• Company Overview
• Income Statement
• Balance Sheet
• Cash Flow Statement
• Earnings Report

There is a demo agent created with PydanticAI in the agent directory, which can be used to test the MCP server. For more information, refer to the Demo Agent section.

🚀 Quick Start

✨ Features

• Bridges the proxy and AlphaVantage financial API.
• Allows AI agents to access financial data and perform financial analysis via MCP.
• Exposes multiple financial data endpoints as MCP tools.

📦 Installation

Prerequisites

• An Azure subscription
• Azure Developer CLI (azd)
• Azure Functions Core Tools
• Python 3.11
• An AlphaVantage API key (see AlphaVantage)

Local Development

1. Clone this repository.
2. Create a virtual environment and install dependencies:

uv sync --frozen

3. Create a local.settings.json file in the src directory and add your AlphaVantage API key:

{
  "IsEncrypted": false,
  "Values": {
    "FUNCTIONS_WORKER_RUNTIME": "python",
    "AzureWebJobsStorage": "UseDevelopmentStorage=true",
    "ALPHAVANTAGE_API_KEY": "your-alphavantage-api-key"
  }
}

4. Run the function locally:

cd src
func start

Deployment

1. Log in to Azure:

azd auth login

2. Deploy the application:

azd up

This will configure the necessary Azure resources and deploy the function app.

⚠️ Important Note

For detailed information on setting environment variables, refer to the Add Environment Variables section.

💻 Usage Examples

Get the MCP Endpoint URL

After deployment, get your MCP extension system key:

az functionapp keys list \
  --resource-group <resource-group> \ 
  --name <function-app-name>

Your MCP endpoint URL will be:

https://<funcappname>.azurewebsites.net/runtime/webhooks/mcp/sse?code=<your-mcp-extension-system-key>

Add Environment Variables

• AZURE_STORAGE_ACCOUNT: The name of the Azure storage account for storage.
• AZURE_STORAGE_KEY: The key associated with the storage account.

VS Code Configuration

Add the following content to src/.vscode/settings.json to configure the Python environment:

{
  "python.defaultInterpreterPath": "${fileDirname}/envs/myenv/Scripts/python.exe"
}

Demo Agent

There is a demo agent created with FastAPI in the agent directory. You can run the following command to test its functionality:

uvicorn agent.main:app --reload

Visit http://localhost:8000 to view the documentation.

📚 Documentation

• Azure Functions Documentation
• FastAPI Documentation
• AlphaVantage API Documentation