flask-mcp-server
MCP server to control a Flask application and optimize AWS costs, providing tools for app management, AWS resource checking, and cost analysis via Claude.
README
Flask MCP Server with AWS Cost Optimizer
<img width="1915" height="940" alt="Screenshot 2025-10-13 020657" src="https://github.com/user-attachments/assets/6e6b80ef-4a2a-4fe3-9cb3-508669d350b5" />
Executive Summary
Enterprise Flask application suite featuring Model Context Protocol (MCP) server integration and a comprehensive AWS cost optimization platform. Designed for production environments with scalable architecture and business-grade reporting capabilities.
Dashboard Features: Professional web interface displaying real-time cost analysis with $147/month tracking and $45 potential savings identification. The dashboard includes interactive charts, cost breakdown visualizations, and AI-powered optimization recommendations with priority rankings.
Repository Structure
flask-mcp-server/
├── aws-cost-optimizer/ # Primary AWS cost optimization platform
│ ├── app.py # Flask web application
│ ├── templates/ # Web dashboard UI
│ ├── static/ # CSS, JavaScript assets
│ ├── services/ # AWS integration services
│ ├── routes/ # REST API endpoints
│ └── mcp/ # Claude Desktop integration
│
├── flask_app_mcp.py # Original MCP server implementation
├── start_flask.py # MCP server utilities
├── test_mcp_server.py # Testing framework
└── requirements.txt # Python dependencies
Primary Project: AWS Cost Optimizer
Business Impact
Cost Reduction Achieved: $45/month savings identified (30.6% reduction)
Resources Monitored: 6 AWS resources across EC2, S3, EBS services
Account Integration: Live connection to AWS account 611377760416
Monthly Cost Tracking: $147.00 with real-time analysis
Enterprise Features
- Health Monitoring: Check app status and endpoints
- Route Discovery: Automatically find Flask routes
- AWS Integration: Connect to AWS services
- Claude AI Integration: Natural language Flask app control
📋 Available Tools
| Tool | Description |
|---|---|
start-flask-app |
Start your Flask application |
stop-flask-app |
Stop the Flask application |
check-flask-status |
Check if Flask is running |
list-flask-routes |
Show all Flask routes |
test-flask-endpoint |
Test specific endpoints |
get-flask-logs |
View application logs |
deploy-to-aws |
Deploy to AWS |
check-aws-resources |
Check AWS resources |
⚙️ Configuration
Edit the .env file:
FLASK_APP_PATH=/path/to/your/flask/app
AWS_REGION=us-west-2
FLASK_HOST=127.0.0.1
FLASK_PORT=5000
🔧 Claude Desktop Setup
Add to your Claude Desktop config:
{
"mcpServers": {
"flask-mcp-server": {
"command": "python",
"args": ["/full/path/to/flask_app_mcp.py"],
"env": {
"AWS_REGION": "us-west-2"
}
}
}
}
📝 License
MIT License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.