Cfm Tips Cost Optimization MCP Server

What is Cfm Tips Cost Optimization MCP Server about?

Cfm Tips Cost Optimization MCP Server delivers a full‑stack, read‑only cost‑analysis engine for AWS environments. It pulls data from native AWS services (Cost Explorer, Compute Optimizer, Trusted Advisor, etc.), runs a library of predefined optimization playbooks, and returns actionable recommendations in JSON or Markdown via an MCP‑compatible interface.

How to use Cfm Tips Cost Optimization MCP Server?

Installation

1. Clone the repository and change into the directory.

   git clone https://github.com/aws-samples/sample-cfm-tips-mcp.git
   cd sample-cfm-tips-mcp
   

2. Install Python dependencies.

   pip install -r requirements.txt
   

3. Configure AWS credentials (CLI configuration or environment variables).
4. Create and attach the read‑only IAM policy listed in the README to the user/role that will run the server.
5. (Optional) Run python3 setup.py to install MCP configuration files.

Running the MCP server

python3 mcp_server_with_runbooks.py

The server communicates over stdio, which can be wired into Amazon Q CLI or any MCP‑compatible client:

q chat          # then ask for cost recommendations

Or configure in the Q Developer Plugin:

• Scope: Global
• Name: cfm‑tips
• Transport: stdio
• Command: python3
• Arguments: <repo‑path>/mcp_server_with_runbooks.py
• Timeout: 60

Typical commands (via chat or API) include:

• get_cost_explorer_data
• ec2_rightsizing
• ebs_optimization
• rds_idle
• lambda_unused
• comprehensive_analysis

Key Features

• Direct integration with AWS Cost Explorer, Cost Optimization Hub, Compute Optimizer, Trusted Advisor, and Performance Insights.
• Pre‑built playbooks for EC2, EBS, RDS, Lambda, and CloudTrail optimization.
• Real CloudWatch metric consumption for accurate usage analysis.
• Report generation in JSON or Markdown with estimated savings and priority ranking.
• Strict least‑privilege IAM requirements (read‑only actions only).
• Easy plug‑in for Amazon Q CLI and other MCP clients.

Use Cases

• FinOps teams: Quickly surface cost‑saving opportunities across multiple services.
• DevOps engineers: Automate periodic right‑sizing checks in CI pipelines.
• Cloud architects: Produce comprehensive cost‑optimization reports for stakeholder reviews.
• Developers: Integrate cost‑analysis queries directly into IDE chat assistants via the Q Developer Plugin.

FAQ

Q: Does the server make any changes to my AWS resources? A: No. It operates with read‑only permissions only and returns recommendations; any remediation must be performed manually or via separate automation.

Q: Which AWS regions are supported? A: All regions supported by the underlying AWS services. Specify the region in your queries or set AWS_DEFAULT_REGION.

Q: How are savings estimates calculated? A: The server uses pricing data from Cost Explorer and the utilization metrics from CloudWatch to project monthly cost reductions for each recommendation.

Q: Can I extend the playbooks? A: Yes. Add new Python functions in runbook_functions.py and reference them in mcp_runbooks.json.

Q: What if I get permission errors? A: Verify that the IAM policy from the README is attached and that Cost Optimization Hub is enabled in the AWS console.

CFM Tips - Cost Optimization MCP Server

A comprehensive Model Context Protocol (MCP) server for AWS cost analysis and optimization recommendations, designed to work seamlessly with Amazon Q CLI and other MCP-compatible clients.

✅ Features

Core AWS Services Integration

• Cost Explorer - Retrieve cost data and usage metrics
• Cost Optimization Hub - Get AWS cost optimization recommendations
• Compute Optimizer - Right-sizing recommendations for compute resources
• Trusted Advisor - Cost optimization checks and recommendations
• Performance Insights - RDS performance metrics and analysis

Cost Optimization Playbooks

• 🔧 EC2 Right Sizing - Identify underutilized EC2 instances
• 💾 EBS Optimization - Find unused and underutilized volumes
• 🗄️ RDS Optimization - Identify idle and underutilized databases
• ⚡ Lambda Optimization - Find overprovisioned and unused functions
• � *CloudTrail Optimization - Analyze and optimize CloudTrail configurations
• 📊 Comprehensive Analysis - Multi-service cost analysis

Advanced Features

• Real CloudWatch Metrics - Uses actual AWS metrics for analysis
• Multiple Output Formats - JSON and Markdown report generation
• Cost Calculations - Estimated savings and cost breakdowns
• Actionable Recommendations - Priority-based optimization suggestions

📁 Project Structure

sample-cfm-tips-mcp/
├── playbooks/                            # CFM Tips optimization playbooks engine
├── services/                             # AWS Services as datasources for the cost optimization
├── mcp_server_with_runbooks.py           # Main MCP server
├── runbook_functions.py                  # Cost optimization runbook implementations
├── mcp_runbooks.json                     # Template file for MCP configuration file
├── requirements.txt                      # Python dependencies
├── test_runbooks.py                      # Integration tests
├── diagnose_cost_optimization_hub_v2.py  # Diagnostic utilities
├── RUNBOOKS_GUIDE.md                     # Detailed usage guide
└── README.md                             # Project ReadMe

🔐 Security and Permissions - Least Privileges

The MCP tools require specific AWS permissions to function.

• Create a read-only IAM role - Restricts LLM agents from modifying AWS resources. This prevents unintended create, update, or delete actions.
• Enable CloudTrail - Tracks API activity across your AWS account for security monitoring.
• Follow least-privilege principles - Grant only essential read permissions (Describe*, List*, Get*) for required services.

The below creates an IAM policy with for list, read and describe actions only:

{
  "Version": "2012-10-17",
  "Statement": [
    {
      "Effect": "Allow",
      "Action": [
        "cost-optimization-hub:ListEnrollmentStatuses",
        "cost-optimization-hub:ListRecommendations",
        "cost-optimization-hub:GetRecommendation", 
        "cost-optimization-hub:ListRecommendationSummaries",
        "ce:GetCostAndUsage",
        "ce:GetCostForecast",
        "compute-optimizer:GetEC2InstanceRecommendations",
        "compute-optimizer:GetEBSVolumeRecommendations",
        "compute-optimizer:GetLambdaFunctionRecommendations",
        "ec2:DescribeInstances",
        "ec2:DescribeVolumes",
        "rds:DescribeDBInstances",
        "lambda:ListFunctions",
        "cloudwatch:GetMetricStatistics",
        "s3:ListBucket",
        "s3:ListObjectsV2",
        "support:DescribeTrustedAdvisorChecks",
        "support:DescribeTrustedAdvisorCheckResult",
        "pi:GetResourceMetrics",
        "cloudtrail:DescribeTrails",
        "cloudtrail:GetTrailStatus",
        "cloudtrail:GetEventSelectors"

      ],
      "Resource": "*"
    }
  ]
}

🛠️ Installation

Prerequisites

• Python 3.11 or higher
• AWS CLI configured with appropriate credentials
• Amazon Q CLI (for MCP integration) - https://docs.aws.amazon.com/amazonq/latest/qdeveloper-ug/command-line-installing.html

Setup Steps

1. Clone the Repository

   git clone https://github.com/aws-samples/sample-cfm-tips-mcp.git
   cd sample-cfm-tips-mcp
   

2. Install Dependencies

   pip install -r requirements.txt
   

3. Configure AWS Credentials

   aws configure
   # Or set environment variables:
   # export AWS_ACCESS_KEY_ID=your_access_key
   # export AWS_SECRET_ACCESS_KEY=your_secret_key
   # export AWS_DEFAULT_REGION=us-east-1
   

4. Apply IAM Permissions

   • Create an IAM policy with the permissions listed above
   • Attach the policy to your IAM user or role

5. Install the MCP Configurations

   python3 setup.py
   

6. Usage Option 1: Using the Q CLI Chat

   q chat
   Show me cost optimization recommendations
   

7. Usage Option 2: Integrate with Amazon Q Developer Plugin or Kiro

   • Open Amazon Q Developer Plugin on your IDE
   • Click on Chat -> 🛠️ Configure MCP Servers -> ➕ Add new MCP
   • Use the following configuration

   - Scope: Global
   - Name: cfm-tips
   - Transport: stdio
   - Command: python3
   - Arguments: <replace-with-path-to-folder>/mcp_server_with_runbooks.py
   - Timeout: 60
   

🔧 Available Tools

Cost Analysis Tools

• get_cost_explorer_data - Retrieve AWS cost and usage data
• list_coh_enrollment - Check Cost Optimization Hub enrollment
• get_coh_recommendations - Get cost optimization recommendations
• get_coh_summaries - Get recommendation summaries
• get_compute_optimizer_recommendations - Get compute optimization recommendations

EC2 Optimization

• ec2_rightsizing - Analyze EC2 instances for right-sizing opportunities
• ec2_report - Generate detailed EC2 optimization reports

EBS Optimization

• ebs_optimization - Analyze EBS volumes for optimization
• ebs_unused - Identify unused EBS volumes
• ebs_report - Generate EBS optimization reports

RDS Optimization

• rds_optimization - Analyze RDS instances for optimization
• rds_idle - Identify idle RDS instances
• rds_report - Generate RDS optimization reports

Lambda Optimization

• lambda_optimization - Analyze Lambda functions for optimization
• lambda_unused - Identify unused Lambda functions
• lambda_report - Generate Lambda optimization reports

Comprehensive Analysis

• comprehensive_analysis - Multi-service cost analysis

Additional Tools

• get_trusted_advisor_checks - Get Trusted Advisor recommendations
• get_performance_insights_metrics - Get RDS Performance Insights data

📊 Example Usage

Basic Cost Analysis

"Get my AWS costs for the last month"
"Show me cost optimization recommendations"
"What are my biggest cost drivers?"

Resource Optimization

"Find underutilized EC2 instances in us-east-1"
"Show me unused EBS volumes that I can delete"
"Identify idle RDS databases"
"Find unused Lambda functions"

Report Generation

"Generate a comprehensive cost optimization report"
"Create an EC2 right-sizing report in markdown format"
"Generate an EBS optimization report with cost savings"

Multi-Service Analysis

"Run comprehensive cost analysis for all services in us-east-1"
"Analyze my AWS infrastructure for cost optimization opportunities"
"Show me immediate cost savings opportunities"

🔍 Troubleshooting

Common Issues

1. Cost Optimization Hub Not Working

   python3 diagnose_cost_optimization_hub_v2.py
   

2. No Metrics Found

   • Ensure resources have been running for at least 14 days
   • Verify CloudWatch metrics are enabled
   • Check that you're analyzing the correct region

3. Permission Errors

   • Verify IAM permissions are correctly applied
   • Check AWS credentials configuration
   • Ensure Cost Optimization Hub is enabled in AWS Console

4. Import Errors

   # Check Python path and dependencies
   python3 -c "import boto3, mcp; print('Dependencies OK')"
   

Getting Help

• Check the RUNBOOKS_GUIDE.md for detailed usage instructions
• Run the diagnostic script: python3 diagnose_cost_optimization_hub_v2.py
• Run integration tests: python3 test_runbooks.py

🧩 Add-on MCPs

Add-on AWS Pricing MCP Server MCP server for accessing real-time AWS pricing information and providing cost analysis capabilities https://github.com/awslabs/mcp/tree/main/src/aws-pricing-mcp-server

# Example usage with Add-on AWS Pricing MCP Server:
"Review the CDK by comparing it to the actual spend from my AWS account's stackset. Suggest cost optimization opportunities for the app accordingly"

🎯 Key Benefits

• Immediate Cost Savings - Identify unused resources for deletion
• Right-Sizing Opportunities - Optimize overprovisioned resources
• Real Metrics Analysis - Uses actual CloudWatch data
• Actionable Reports - Clear recommendations with cost estimates
• Comprehensive Coverage - Analyze EC2, EBS, RDS, Lambda, and more
• Easy Integration - Works seamlessly with Amazon Q CLI

📈 Expected Results

The CFM Tips cost optimization server can help you:

• Identify cost savings on average
• Find unused resources costing hundreds of dollars monthly
• Right-size overprovisioned instances for optimal performance/cost ratio
• Optimize storage costs through volume type recommendations
• Eliminate idle resources that provide no business value

🤝 Contributing

We welcome contributions! Please see our contributing guidelines:

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Add tests for new functionality
5. Submit a pull request

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.

---