awslabs.billing-cost-management-mcp-server
AWS does not publish a dedicated Compute Optimizer MCP server. The official AWS Labs "Billing and Cost Management" MCP server surfaces Compute Optimizer rightsizing recommendations (EC2, Auto Scaling groups, EBS, ECS on Fargate, Lambda, RDS, and idle resources) alongside Cost Explorer, Cost Optimization Hub, and pricing tools. It is an open-source, locally run stdio server.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Documentation
Documentation link · transport stdio
Tools
get_ec2_instance_recommendations— Return Amazon EC2 instance rightsizing recommendations.get_auto_scaling_group_recommendations— Return Auto Scaling group recommendations.get_ebs_volume_recommendations— Return Amazon EBS volume recommendations.get_ecs_service_recommendations— Return Amazon ECS service (Fargate) recommendations.get_lambda_function_recommendations— Return AWS Lambda function recommendations.get_rds_database_recommendations— Return Amazon Aurora and RDS database recommendations.get_idle_recommendations— Return idle resource recommendations.get_enrollment_status— Return the Compute Optimizer enrollment (opt-in) status of the account.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.