Amazon Ads MCP

Amazon Ads MCP server.

agentcentral includes a hosted Amazon Ads MCP server surface for querying campaigns, ad groups, keywords, search terms, placements, budget pacing, TACOS, and retained performance history. It also exposes Amazon source-provided bid and budget suggestion fields and optional guarded ads write tools when a key is scoped for writes.

The ads tools are part of the broader agentcentral Amazon seller MCP data layer, so an AI client can join ad performance with orders, inventory, catalog, ranking, and finance context.

Last updated May 7, 2026.

Start 7-day free trial Ads overview

Ads surface: 38 Amazon Ads tools across reads, live Amazon fields, and guarded writes
Endpoint: https://mcp.agentcentral.to/mcp
Metrics: Spend, sales, ACOS, ROAS, CTR, CVR, TACOS, pacing, and placements
History: Daily snapshots and retained reporting rows from connection forward
Write access: Optional ads write tools with pre-read checks and audit logs
Client support: Claude, ChatGPT, OpenClaw, Cursor, and custom MCP clients

Hosted MCP endpoint

Header-capable MCP clients use https://mcp.agentcentral.to/mcp with an agentcentral bearer key.

Scoped access

API keys can be read-only, domain-scoped, or include supported write tools for a specific workflow.

Data-layer boundary

agentcentral returns source fields, normalized joins, deterministic metrics, classifications, and audit results.

Data coverage

What the MCP server exposes.

The hosted server is built around factual seller data that an AI client can query repeatedly. The client does the reasoning; the agentcentral tools provide the structured data surface.

Campaign performance

Campaign, portfolio, ad group, keyword, product, purchased product, placement, Store, DSP, and attribution performance rows.

Search terms and keywords

Search term rows, keyword performance, search query ad coverage, brand health, share of voice, and SQP joins.

Budget and bid fields

Budget pacing plus Amazon Ads API bid and budget suggestion fields labeled as Amazon-provided data.

Guarded ads writes

Supported bid, budget, campaign, keyword, ad group, audience adjustment, and negative keyword changes can be scoped per key.

Access model

How AI clients connect.

Connect Amazon once, let agentcentral sync the seller data, then give the AI client a scoped MCP credential or connector URL.

Connect Amazon Ads

Authorize Amazon Ads in the dashboard; agentcentral handles token refresh and reporting syncs.

Retain history

Campaign snapshots, report rows, and budget usage data are stored so follow-up questions can reuse context.

Scope ads access

Create an ads-only key, a read-only key, or a key that includes selected write tools.

Use MCP from the client

Add the hosted MCP endpoint to Claude, ChatGPT, or a custom client that supports remote MCP.

Deeper setup and reference material.

Use these pages for setup, tool coverage, and client-specific configuration details.

Amazon Ads agent page

Ads-focused overview with examples and tool coverage.

Open page

Ads tool reference

Parameter-level reference for Amazon Ads MCP tools.

Open page

Amazon Seller MCP

Full seller data layer overview beyond ads.

Open page

Claude quickstart

Connect the hosted MCP endpoint to Claude.

Open page

FAQ

Common questions.

What MCP server works with Amazon Ads?+

agentcentral works as a hosted Amazon Ads MCP server and exposes campaign, keyword, search term, budget, TACOS, and guarded write tools through MCP.

Can an AI agent update Amazon Ads through agentcentral?+

Yes, only when the API key includes ads write tools. Write tools pre-read current values, enforce limits where applicable, and write audit records.

Does agentcentral return Amazon bid recommendations?+

agentcentral can relay Amazon Ads source-provided bid and budget suggestion fields through live Amazon Ads API tools, with the source made clear.

Can ads data be joined with inventory or orders?+

Yes. The broader Full Suite data layer includes inventory, orders, catalog, ranking, finance, and fulfillment data that can be queried through the same MCP server.

Use agentcentral as the Amazon seller data layer.

Start a 7-day free trial, connect Amazon, and create a scoped MCP key or connector URL for the AI client you use.

Start 7-day free trial Tool reference