A sample MCP server for understanding cloud spend

Created By
aws-samplesa year ago
MCP for AWS Cost Explorer and CloudWatch logs
Overview

What is the Sample Cloud Spend MCP Server?

The Sample Cloud Spend MCP Server is a tool designed to help users analyze and visualize their AWS cloud spending data using the AWS Cost Explorer and Amazon Bedrock usage data through an interactive interface powered by Anthropic's Model Control Protocol (MCP).

How to use the Sample Cloud Spend MCP Server?

To use the server, you can run it locally or on Amazon EC2. Users can interact with the server via the Claude Desktop application or a LangGraph Agent, asking questions about their AWS spending in natural language.

Key features of the Sample Cloud Spend MCP Server?

  • Amazon EC2 Spend Analysis: Detailed breakdowns of EC2 spending for the last day.
  • Amazon Bedrock Spend Analysis: Breakdown by region, users, and models over the last 30 days.
  • Service Spend Reports: Analyze spending across all AWS services for the last 30 days.
  • Detailed Cost Breakdown: Granular cost data by day, region, service, and instance type.
  • Interactive Interface: Natural language queries through Claude.

Use cases of the Sample Cloud Spend MCP Server?

  1. Understanding daily EC2 spending.
  2. Analyzing Bedrock usage over time.
  3. Generating reports on AWS service spending.
  4. Querying cost data using natural language.

FAQ from the Sample Cloud Spend MCP Server?

  • Can I run the server locally?
    Yes, the server can be run locally or on Amazon EC2.

  • What are the prerequisites?
    You need Python 3.12, AWS credentials with Cost Explorer access, and optionally, access to Amazon Bedrock.

  • Is there a demo available?
    Yes, a demo video is provided to showcase the server's capabilities.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
aws-samples
Star
0
Language
Python
License
MIT-0 license

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago