AWS Billing MCP Server — 11 AI Tools

AWS Billing MCP ServerAWS Billing MCP server with 11 ready-to-use AI tools. Connect AWS Billing to Claude, ChatGPT, Gemini, or any MCP-compatible AI assistant. Cloud MCP connector — no install, no Docker, works from any browser.Category: Developer Tools. 11 tools available. Authentication: API Key.Automate your AWS billing reports with AIWhy AWS Billing + AI?Navigating the AWS Billing Console for cost analysis is time-consuming. Stop clicking through dashboards and let AI query your costs, compare periods, forecast spending, and manage budgets through natural conversation.Example prompts you can send your AI about AWS Billing

Ask: "What are my top 5 most expensive AWS services this month?"
AI does: AI queries Cost Explorer grouped by SERVICE, sorts by cost, and shows your top services with amounts and percentage of total spend.

Ask: "How much will I spend on AWS next month?"
AI does: AI generates a cost forecast with prediction intervals, showing the expected amount and upper/lower confidence bounds.

Ask: "Create a $3000 monthly budget for production and alert me at 80%"
AI does: AI creates the budget with a cost filter for your production account, sets up an 80% threshold notification to your email.

Ask: "Which EC2 instances are oversized?"
AI does: AI retrieves rightsizing recommendations showing current vs recommended instance types, estimated monthly savings, and performance risk.

Featured AWS Billing Tools

get-cost-and-usage: Retrieve AWS costs and usage data for a specific time period. This is your PRIMARY tool for answering any question about "how much did I spend?" or "what are my AWS costs?". You can break down costs by SERVICE (e.g., EC2, S3, Lambda), REGION (us-east-1, eu-west-1), LINKED_ACCOUNT (for AWS Organizations with multiple accounts), or INSTANCE_TYPE (m5.large, t3.micro). Returns cost amounts in USD with line items per group. CRITICAL DATE RULES — READ THIS CAREFULLY: • endDate is EXCLUSIVE — it is NOT included in the results. • To get January costs: startDate="2025-01-01" and endDate="2025-02-01" • To get January + February: startDate="2025-01-01" and endDate="2025-03-01" • To get a full year 2025: startDate="2025-01-01" and endDate="2026-01-01" • WRONG: startDate="2025-01-01" and endDate="2025-01-31" — This MISSES January 31st! • WRONG: startDate="2025-01-01" and endDate="2025-01-30" — This MISSES 2 days! • CORRECT: Always set endDate to the FIRST DAY of the NEXT month/period. ALWAYS USE groupBy WITH SERVICE unless the user asks for something else. Without groupBy you only get a single total number which is almost never useful. COPY-PASTE groupBy FORMAT: • By service: [{"type":"DIMENSION","key":"SERVICE"}] • By region: [{"type":"DIMENSION","key":"REGION"}] • By service AND region: [{"type":"DIMENSION","key":"SERVICE"},{"type":"DIMENSION","key":"REGION"}] GRANULARITY RULES: • Use MONTHLY for most queries (cost per month overview). • Use DAILY only for short recent periods (last 14 days max). • NEVER use HOURLY — it is not useful for cost queries. COMPLETE EXAMPLES: Example 1 — "How much did I spend in January 2026?": startDate="2026-01-01", endDate="2026-02-01", granularity="MONTHLY", groupBy=[{"type":"DIMENSION","key":"SERVICE"}] Example 2 — "Show me costs for all of 2025": startDate="2025-01-01", endDate="2026-01-01", granularity="MONTHLY", groupBy=[{"type":"DIMENSION","key":"SERVICE"}] Example 3 — "How much did EC2 cost last month?": startDate="2026-01-01", endDate="2026-02-01", granularity="MONTHLY", filter={"Dimensions":{"Key":"SERVICE","Values":["Amazon Elastic Compute Cloud - Compute"]}} Example 4 — "Daily costs for the last week": startDate="2026-02-08", endDate="2026-02-15", granularity="DAILY", groupBy=[{"type":"DIMENSION","key":"SERVICE"}] WHEN TO USE: User asks about costs, spending, bills, invoices, expenses, top services, cost breakdown, cost by region/account, or "how much did I spend on X?". COST: Each API call costs $0.01 USD.

get-cost-forecast: Predict future AWS spending based on historical usage patterns. Returns a forecasted total cost plus confidence intervals (80% confidence range with lower and upper bounds). CRITICAL RULES: • startDate MUST be today or a future date. You CANNOT forecast the past. • The AWS account must have at least 30 days of historical data for forecasting to work. • If the account is very new and this tool fails, use get-cost-and-usage to show current trends instead. DATE RULES — endDate is EXCLUSIVE: • Forecast for March 2026: startDate="2026-03-01", endDate="2026-04-01" • Forecast for rest of current month (mid-February): startDate="2026-02-15", endDate="2026-03-01" • Forecast next 3 months: startDate="2026-03-01", endDate="2026-06-01" WHEN TO USE: User asks about future costs, projections, forecasts, estimates, "how much will I spend next month?", or budget planning questions.

get-cost-comparison: Compare AWS costs between two time periods side by side. Returns both periods' cost data so you can calculate the difference and identify which services increased or decreased. HOW IT WORKS: You provide two date ranges — a "previous" (older) period and a "current" (newer) period. The tool returns costs for both so you can compare them. CRITICAL DATE RULES — endDate is EXCLUSIVE in BOTH periods: • Compare January vs February 2026: previousStart="2026-01-01", previousEnd="2026-02-01", currentStart="2026-02-01", currentEnd="2026-03-01" • Compare Q4 2025 vs Q1 2026: previousStart="2025-10-01", previousEnd="2026-01-01", currentStart="2026-01-01", currentEnd="2026-04-01" • Compare this year vs last year (January): previousStart="2025-01-01", previousEnd="2025-02-01", currentStart="2026-01-01", currentEnd="2026-02-01" IMPORTANT: "previous" = the OLDER period. "current" = the NEWER/RECENT period. Do NOT mix them up. ALWAYS INCLUDE groupBy: [{"type":"DIMENSION","key":"SERVICE"}] — without this you only get totals which are useless for understanding WHAT changed. WHEN TO USE: User asks to compare periods, asks "why did my costs go up?", requests month-over-month trends, asks "what changed between X and Y?", or wants to see spending changes between any two time ranges.

list-budgets: List all AWS budgets on the account. For each budget, shows: budget name, type (COST/USAGE), limit amount, actual current spend, forecasted end-of-period spend, and percentage consumed. Use this tool FIRST to see what budgets exist before trying to get details or update a specific budget. If no budgets exist, suggest creating one with create-budget. WHEN TO USE: User asks "what budgets do I have?", "how are my budgets doing?", "am I over budget?", "show my budget status", or any question about existing budgets.

create-budget: Create a new AWS budget with optional email alert notifications. A budget sets a spending limit and can alert the user when actual or forecasted costs cross a threshold. WHAT YOU CAN CONFIGURE: • Budget name — must be unique in the account (e.g., "Monthly-Total", "EC2-Budget") • Spending limit — amount in USD • Time unit — how often the budget resets: MONTHLY (most common), DAILY, QUARTERLY, or ANNUALLY • Cost filters — limit the budget to specific services or regions • Email notifications — send email when spending reaches a percentage of the budget IMPORTANT — budgetLimit.amount MUST BE A STRING, NOT A NUMBER: • CORRECT: {"amount": "5000", "unit": "USD"} • WRONG: {"amount": 5000, "unit": "USD"} COMPLETE EXAMPLES: Example 1 — Simple monthly budget of $100: budgetName="Monthly-Total", budgetLimit={"amount":"100","unit":"USD"}, timeUnit="MONTHLY" Example 2 — EC2-only budget of $50/month: budgetName="EC2-Monthly", budgetLimit={"amount":"50","unit":"USD"}, timeUnit="MONTHLY", costFilters={"Service":["Amazon Elastic Compute Cloud - Compute"]} Example 3 — Budget with email alert at 80%: budgetName="Production-Monthly", budgetLimit={"amount":"5000","unit":"USD"}, timeUnit="MONTHLY", notifications=[{"threshold":80,"subscriberEmail":"admin@company.com"}] Example 4 — Budget with multiple alerts (50%, 80%, 100%): budgetName="All-Services", budgetLimit={"amount":"200","unit":"USD"}, timeUnit="MONTHLY", notifications=[{"threshold":50,"subscriberEmail":"team@company.com"},{"threshold":80,"subscriberEmail":"team@company.com"},{"threshold":100,"subscriberEmail":"team@company.com"}] WHEN TO USE: User asks to "create a budget", "set a spending limit", "set up cost alerts", "notify me when costs reach X", or "I want a budget for EC2".

get-rightsizing-recommendations: Get EC2 rightsizing recommendations to find instances that are too large for their workload (overprovisioned) or barely used (idle). This is the BEST starting point for AWS cost optimization. For each recommendation, shows: • Current instance type and its monthly cost • Recommended action: "Modify" (resize to smaller/cheaper instance) or "Terminate" (instance is idle, stop paying for it) • Recommended instance type and estimated monthly cost after the change • Estimated monthly savings in dollars • Performance risk: Very Low, Low, Medium, or High (lower risk = safer to change) LIMITATIONS: • Only works for Amazon EC2 instances (not RDS, Lambda, etc.) • Requires Cost Explorer to be enabled in the AWS account WHEN TO USE: User asks "how can I reduce my AWS costs?", "which instances should I resize?", "are any EC2 instances oversized?", "find idle instances", "cost optimization recommendations", or "I want to save money on AWS".

Frequently Asked Questions about AWS BillingHow do I connect AWS Billing to Claude or ChatGPT?Create a free LearnToSpeak.ai account, add your AWS Billing credentials in the dashboard, and paste the generated OAuth URL into Claude.ai's custom connectors or ChatGPT's developer apps. The integration runs fully in the cloud — no desktop app, no CLI, no local install.Does it cost anything to connect AWS Billing?The AWS Billing integration is free during the LearnToSpeak.ai public beta. You only need a paid plan from Anthropic or OpenAI (Claude Pro/Max/Team or ChatGPT Plus/Pro/Team) since custom connectors require it on the AI provider side.Which AI assistants support the AWS Billing connector?Claude.ai (Pro, Max, Team, Enterprise) and ChatGPT (Plus, Pro, Team) both support the AWS Billing integration via the MCP (Model Context Protocol) standard. The same credentials work across both platforms — add the connector once, use it everywhere.How many AWS Billing tools does my AI get access to?Your AI gets 11 ready-to-use tools for AWS Billing, covering the most common read and write operations. Each tool is a discrete action the AI can call on demand — no multi-step prompting, no screen scraping, no workarounds.Is it safe to give an AI access to my AWS Billing account?Yes. Your AWS Billing credentials are encrypted at rest with AES-256-GCM and only decrypted in memory when the AI makes a request. LearnToSpeak.ai uses OAuth 2.1 with mandatory PKCE for the AI-to-platform connection, and you can revoke access instantly from the dashboard. We never store or log the actual tool responses returned to the AI.Why use LearnToSpeak.ai instead of running an MCP server locally?Cloud MCP servers work from any browser on any device — no Node.js install, no Docker, no local ports, no maintenance. Configure AWS Billing once in the dashboard and your AI connects from claude.ai or chat.openai.com directly. That's the entire value proposition: web AI assistants don't read your filesystem, they read our servers.What is the AWS Billing MCP server?The AWS Billing MCP server is a cloud-hosted integration that gives AI assistants direct access to AWS Billing through 11 tools via the Model Context Protocol (MCP) standard. It works with Claude, ChatGPT, Gemini, and any MCP-compatible AI — no local installation or Docker required.How do I connect AWS Billing to Claude via MCP?Sign up at LearnToSpeak.ai, add your AWS Billing credentials, and copy the generated MCP URL into Claude.ai's custom connectors (Settings → Developer → Custom Connectors). The cloud MCP server handles the connection — no CLI, no local server, no Docker.How do I connect AWS Billing to ChatGPT via MCP?Sign up at LearnToSpeak.ai, add your AWS Billing credentials, and copy the generated MCP URL into ChatGPT's developer apps (Settings → Apps → Advanced → Developer mode). Works with any ChatGPT Plus, Pro, or Team account.What can AI do with AWS Billing through MCP?AWS Billing offers 11 MCP tools covering Query AWS costs, forecast spending, manage budgets, and get rightsizing recommendations. Ask your AI to perform any of these actions in natural language — it calls the right tool automatically.What is MCP (Model Context Protocol)?MCP is an open standard that lets AI assistants like Claude, ChatGPT, and Gemini connect directly to external apps and services. LearnToSpeak.ai hosts cloud MCP servers so you don't need to install anything locally — your AI connects from any browser.Related MCP Servers

GitHub MCP Server — 44 tools

GitLab MCP Server — 90 tools

NetBox MCP Server — 179 tools

Cisco CPNR MCP Server — 36 tools

Grafana MCP Server — 50 tools

Browse all 34 MCP servers