AWS Trusted Advisor MCP サーバー

Created By
enomoto11a year ago
AWS Trusted Advisor MCP Server - 低利用率EC2インスタンスの停止やEBSスナップショットの作成など、AWS環境の最適化を提案するツール
Overview

What is AWS Trusted Advisor MCP Server?

AWS Trusted Advisor MCP Server is a tool that leverages the features of AWS Trusted Advisor to suggest optimizations for your AWS environment, such as stopping underutilized EC2 instances and creating EBS snapshots.

How to use AWS Trusted Advisor MCP Server?

To use the server, clone the repository, install dependencies, and run the server in development mode or using Docker. Configure AWS credentials to allow access to Trusted Advisor and related services.

Key features of AWS Trusted Advisor MCP Server?

  • Suggests stopping underutilized EC2 instances based on Trusted Advisor checks.
  • Proposes creating snapshots for EBS volumes that lack backups.
  • Detects exposed IAM access keys and suggests their deactivation.
  • Identifies S3 buckets that do not have versioning enabled and suggests enabling it.

Use cases of AWS Trusted Advisor MCP Server?

  1. Identifying and stopping low-utilization EC2 instances.
  2. Creating backups for EBS volumes that need snapshots.
  3. Ensuring security by deactivating exposed IAM access keys.
  4. Managing S3 bucket versioning for data protection.

FAQ from AWS Trusted Advisor MCP Server?

  • Can this tool make changes to my AWS environment?

No, this tool only suggests changes and does not perform any actions directly.

  • What are the prerequisites for running this server?

You need Node.js 14 or higher, npm or yarn, and an AWS account with appropriate IAM permissions.

  • Is there a Docker option for running this server?

Yes, the server can be run in a Docker container.

Project Info
Created At
a year ago
Updated At
a year ago
Author Name
enomoto11
Star
0
Language
TypeScript
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