Introduction
This article can be useful for FinOps engineers who want to automate their monthly cost reporting workflow. FinOps is all about managing cloud costs efficiently, but creating consistent executive reports every month is time-consuming and error-prone. Most companies spend heavily on cloud infrastructure, and CTOs need clear, standardized reports to track spending trends. As a FinOps engineer, you need a system that generates professional cost reports with the same structure every month — not ad-hoc prompts that vary in quality. In this article, I’ll show you how to build a Claude Skill that combines MCP Server with AWS Cost Explorer to create deterministic, executive-ready cost reports in just 3 minutes. Once configured, you’ll never need to generate complex prompts again.
What is MCP Server?
MCP (Model Context Protocol) Server is a technology that allows AI assistants like Claude to connect directly to external tools and data sources. Think of it as a bridge between Claude and your cloud infrastructure.
In our case, the AWS Cost Explorer MCP Server enables Claude to make API calls to AWS Cost Explorer, fetch your actual spending data, analyze usage patterns, and retrieve detailed cost breakdowns — all in real-time. Without MCP, you’d need to manually export cost data from AWS, format it, and paste it into Claude. With MCP, Claude accesses the data directly and automatically.
What Are Claude Skills?
Think of Claude Skills as reusable expert templates. Instead of explaining your requirements every single time, you create a skill file that contains all your instructions, preferences, and guidelines. Claude then follows this “playbook” perfectly every time you invoke it.
For FinOps reporting, this means:
- Same professional structure every month
- Consistent analysis framework
- No forgotten requirements
- Executive-ready format guaranteed
Prerequisites for Claude Skill Creation
Before creating the skill, you need to set up the necessary tools and permissions:
- Install Claude Desktop — Download and install from claude.ai/download
- Add AWS Cost Explorer MCP Server — Configure the MCP server in your Claude Desktop settings by adding it to your configuration file
- Configure AWS IAM Permissions — Create an IAM user with Cost Explorer read permissions and configure the credentials
Detailed setup instructions for the MCP server and IAM configuration can be found in the AWS Cost Explorer MCP Server documentation.
Creating an AWS Cost Report Skill
Creating a Claude Skill is straightforward. You simply ask Claude: “Help me create a skill for generating monthly AWS cost reports.”
Claude will then guide you through a series of clarifying questions to understand your specific requirements:
- What data sources and tools you’re using
- How you organize your infrastructure (tags, environments)
- What report structure your executives expect
- What level of detail and visualizations you need
- What analysis and recommendations should be included
Based on your answers, Claude automatically generates a skill file containing detailed, structured instructions. This file defines exactly how Claude should fetch data, analyze it, generate visualizations, and format the final report.
Once the skill is created and saved in Claude Desktop, using it is incredibly simple. Just print this command in Claude prompt:
Use the AWS Cost CEO Report skill to compare November and December 2025 costs.
That’s it. Claude follows the instructions in the skill file and delivers a consistent, professional report every time.
Here is an example of Claude Skill reference file:
# AWS Cost CEO Report Skill - Quick Reference
## 🚀 Quick Start
AWS cost report for the CEO - September vs October 2025
## ✅ Prerequisites Checklist
- [ ] All Cost Explorer MCP servers are started
- [ ] You have cost data for the months you want to compare
## 🎯 Trigger Phrases
| What to Say | What It Does |
|-------------|--------------|
| "AWS cost report for the CEO" | Generates full report for all accounts |
| "Compare September vs October 2025" | Month-to-month comparison |
| "Production account only" | Limits to single account |
| "We implemented VPC endpoints..." | Includes savings actions analysis |
## 📊 Report Includes
✅ Executive summary with key metrics
✅ Visual charts and graphs
✅ Per-account breakdowns
✅ Cost driver analysis
✅ Optimization recommendations
✅ PDF export capability
## 🎨 Report Filters
- Shows only services with >$50/month spend
- Analyzes services with >10% change OR >$100 change
- Focuses on top cost drivers
## 💡 Pro Tips
1. **Monthly Cadence**: Generate reports at the end of each month
2. **Include Context**: Mention infrastructure changes or savings actions
3. **Review Trends**: Look for unexpected cost increases
4. **Act on Recommendations**: Review the optimization section
5. **Export PDF**: Use browser print function to save as PDF
## 🚨 Common Issues
| Issue | Solution |
|-------|----------|
| MCP servers not accessible | Start Docker Desktop and MCP containers |
| Invalid month format | Use "September 2025" not "9/2025" |
| No data returned | Check dates aren't in future |
## 📈 Cost Optimization Areas Analyzed
- EC2 instance rightsizing
- NAT Gateway optimization (VPC endpoints)
- Data transfer costs
- Idle resources
- Over-provisioned infrastructure
- Development environment scheduling
- Storage lifecycle policies
- Reserved Instance opportunities
## 🎓 Example Requests
**Basic Report:**
Generate AWS cost report for the CEO comparing September vs October 2025
**With Savings Context:**
AWS cost report for September vs October 2025.
Actions taken:
- Implemented VPC endpoints
- Migrated to Graviton instances
- Enabled S3 Intelligent Tiering
## 📦 Skill Components
- Main workflow instructions (SKILL.md)
- MCP usage patterns (references/mcp-usage.md)
- Report structure guide (references/report-structure.md)
- HTML template reference (scripts/generate_report.py)
## 🔍 Analysis Depth
**Level 1**: Service-level cost comparison
**Level 2**: Usage-type breakdown (instance types, hours)
**Level 3**: Root cause identification
**Level 4**: Contextual analysis with recommendations
## 💰 Cost Leak Detection
The skill automatically flags:
- Unexpected spikes >20%
- High data transfer costs
- NAT Gateway optimization opportunities
- Idle resources
- Over-provisioned instances
- 24/7 dev/test environments
- Legacy unused resources
## 📄 Export to PDF
1. Open artifact in new window
2. Press Ctrl+P (or Cmd+P on Mac)
3. Select "Save as PDF"
4. Adjust settings if needed
5. Save and share!
Benefits for FinOps Teams:
- Reproducibility: Same report quality every month
- Scalability: Easy to generate reports for multiple accounts/regions
- Compliance: Standardized format satisfies audit requirements
- Onboarding: New team members can generate reports without training
- Evolution: Update the skill once to improve all future reports
Conclusion
MCP Server combined with Claude Skills transforms FinOps reporting from a day-long manual process into a 3-minute automated workflow. You get the speed of AI-powered analysis with the consistency and professionalism that executive leadership demands.
Top comments (0)