MCP.so
ログイン

Agent Central MCP Server

@agentcentral-to

基本情報

カテゴリ

データと分析

トランスポート

stdio

認証方式

oauth

作者

agentcentral-to

投稿者

christi4nity

Agent Central MCP Server について

agentcentral is a hosted MCP server for Amazon sellers that connects Claude, ChatGPT, and other AI clients to Amazon Ads, Seller Central, inventory, orders, catalog, rankings, finance, and fulfillment data.

Agent Central MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "agentcentral": {
      "url": "https://mcp.agentcentral.to/mcp",
      "headers": {
        "Authorization": "Bearer ac_live_<YOUR_API_KEY>"
      }
    }
  }
}

Agent Central MCP Server のツール

1

Get started with agentcentral — returns setup instructions

概要

What is Agent Central?

Agent Central connects the AI you already use to your Amazon Seller Central account. Sellers and agencies can use Claude, ChatGPT, Cursor, Claude Code, and other compatible MCP clients to work with their Amazon account data.

Data coverage

Coverage includes Amazon Ads, inventory, orders, catalog, finance, and fulfillment across 23 Amazon marketplaces. Advertising coverage includes Sponsored Products, Sponsored Brands, Sponsored Display, Amazon DSP, and Stores.

The full catalog contains 177 domain-scoped tools and 5 utilities, 182 tools in total. Available tools depend on the connected account and the scope and permissions of its key.

How to connect

Create an Agent Central account, authorize Seller Central and Amazon Ads through Amazon's own authorization pages, then follow the setup guide for your AI client.

The hosted Streamable HTTP endpoint is https://mcp.agentcentral.to/mcp. Header-capable clients authenticate with Authorization: Bearer ac_live_<YOUR_API_KEY>. Claude custom connectors can use a signed Connector URL generated in the dashboard. There is no local Agent Central server to install.

Setup guide: https://agentcentral.to/docs/quickstart/claude

Access and safeguards

Keys can be read-only or limited to specific areas. Supported account changes use previews, guardrails, and audit logs. Historical data is retained while the account is active, enabling comparisons where that history is available.

Agent Central returns account facts and calculated metrics. The connected AI interprets the information; Agent Central is not a recommendation engine.

Example questions

  • Which campaigns had the highest ACOS last month?
  • Which products have fewer than 21 days of inventory coverage?
  • How did sales, advertising spend, and TACOS change between periods?
  • Which listings are suppressed, and what reasons does Amazon report?

コメント

「データと分析」の他のコンテンツ