Amazon Seller MCP hub

Amazon Seller Central MCP server.

agentcentral is a hosted Amazon Seller MCP server for Seller Central and Amazon Ads data. Claude, ChatGPT, and other AI clients can query ads, inventory, orders, catalog, ranking, finance, fulfillment, and retained history through one remote MCP endpoint with 144 domain-scoped tools.

Use this page as the main Amazon Seller Central MCP overview. The Claude, ChatGPT, Ads, docs, and comparison pages cover narrower setup paths; this hub explains the hosted seller data layer, client access model, domain coverage, and how agentcentral differs from a raw SP-API wrapper or Ads-only MCP surface.

Last updated May 20, 2026.

Product type
Hosted Amazon Seller MCP server and seller data layer
Primary use case
Connect Seller Central and Amazon Ads data to AI clients through MCP
Endpoint
https://mcp.agentcentral.to/mcp
Tool count
144 domain-scoped tools plus 4 utility tools
Data domains
Ads, inventory, orders, catalog, ranking, finance, fulfillment
History
Retained while the account is active; year-over-year comparisons work where history exists
Client support
Claude, ChatGPT, OpenClaw, Hermes Agent, Cursor, and HTTP-capable MCP clients
Write access
Optional per key, with guardrails and audit logs where supported

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

Every seller domain under one Amazon Seller MCP endpoint.

This is the canonical overview page for generic Amazon Seller MCP and Amazon Seller Central MCP searches. agentcentral pulls ads, inventory, orders, catalog, ranking, finance, and fulfillment into one hosted MCP surface, so an agent can move between domains without juggling separate Amazon report flows.

Amazon Ads

Campaigns, keywords, search terms, placements, budgets, TACOS, Store performance, DSP, and Amazon source-provided suggestion fields.

Inventory and orders

FBA inventory, AWD, inbound shipments, days of cover, active listings, suppressed listings, orders, returns, and reimbursements.

Catalog and ranking

Product details, variations, A+ Content, listing quality, listing issues, product reviews, keyword ranks, and search-volume joins.

Finance and fulfillment

Fee breakdowns, profitability, settlement economics, MCF shipping previews, MCF orders, tracking, and returns.

Access model

One Amazon connection, scoped MCP credentials.

You authorize Seller Central and Amazon Ads a single time, agentcentral keeps the seller data synced, and each AI client reads it through a scoped key or connector URL that you control from the dashboard.

Connect Amazon

Authorize Amazon Ads and Seller Central with OAuth from the agentcentral dashboard.

Sync, normalize, retain history

agentcentral syncs, normalizes, and retains seller history while your account is active for fast repeated reads and prior-period comparisons.

Create a scoped key

Give each AI client read-only access, domain-limited access, or selected write tools.

Configure the client

Use a bearer-key MCP config or a signed connector URL for clients that need one.

Related pages

Support pages for Claude, ChatGPT, Ads, docs, and comparisons.

Use this hub for the generic Amazon Seller Central MCP explanation. Follow the narrower pages below when you want setup detail for Claude, ChatGPT, Amazon Ads, tool references, or vendor comparisons.

Amazon Seller Central MCP for Claude

Claude-specific setup and prompts for the same hosted Amazon Seller MCP server.

Open page

Amazon Seller Central MCP for ChatGPT

ChatGPT-specific setup for Seller Central, Amazon Ads, inventory, orders, catalog, ranking, finance, and fulfillment data.

Open page

Amazon Ads MCP server

Answer-first page for Amazon Ads campaign, keyword, search term, budget, TACOS, and Amazon source-provided fields.

Open page

Amazon Ads MCP server for Claude

Claude-specific answer page for Amazon Ads MCP tools and setup.

Open page

Connect Amazon Ads to Claude

Direct setup path for connecting Amazon Ads data to Claude through MCP.

Open page

Amazon seller data layer

Data-layer overview for AI agents querying Amazon seller data across domains.

Open page

Claude connection walkthrough

Step-by-step path from Amazon Seller Central to Claude.

Open page

Claude quickstart

Set up the hosted MCP endpoint in Claude.

Open page

ChatGPT quickstart

Set up the hosted MCP endpoint in ChatGPT.

Open page

Create an account

Open the signup flow and connect Amazon Seller Central.

Open page

Ads tool reference

Campaign, keyword, search term, budget, TACOS, and guarded ads-write tool parameters.

Open page

Catalog tool reference

Product details, listing quality, catalog cleanup, and listing write tool parameters.

Open page

Ranking tool reference

Keyword rank positions, changes, and search-volume joined rank views.

Open page

Finance tool reference

Finance tools for fees, profitability, transactions, and settlement economics.

Open page

Fulfillment tool reference

Multi-Channel Fulfillment previews, order creation, tracking, and returns.

Open page

Tool reference overview

Reference docs for ads, inventory, catalog, ranking, finance, and fulfillment tools.

Open page

Amazon seller MCP servers compared

Comparison page for official Ads MCP, Seller Central connectors, local repos, automation MCPs, and hosted seller data layers.

Open page

Example prompts

What an AI client can ask for.

Ask for source fields, date windows, and explicit metrics. agentcentral returns the data surface; the AI client reasons over it.

Compare this month’s total sales, ad spend, TACOS, orders, and units to the same month last year by ASIN.
Show Prime Day week this year vs last year for top advertised ASINs: sales, ad spend, TACOS, conversion rate, days of cover, and rank movement.
Find SKUs where current days of cover is below the same seasonal week last year, including inbound units and sales velocity.
Compare Buy Box win rate and competitive price history for these ASINs against sales velocity over the last 90 days.

FAQ

Common questions.

Can an AI agent connect to Amazon Seller Central through MCP?+

Yes. agentcentral exposes Amazon Seller Central and Amazon Ads data through a hosted Amazon Seller MCP server after the seller connects Amazon with OAuth.

Is this an Amazon Seller MCP server or an Amazon Ads MCP server?+

agentcentral is broader than an Ads-only MCP surface. Amazon Ads is one supported domain; the same hosted MCP endpoint also exposes Seller Central inventory, orders, catalog, ranking, finance, fulfillment, retained history, and source-attributed seller data.

Does Amazon have an official Seller Central MCP server?+

The public Amazon MCP documentation currently centers on Amazon Ads. Seller Central MCP access generally comes from third-party connectors, local MCP repos, automation platforms, or hosted seller data layers like agentcentral.

Does agentcentral require a local MCP server?+

No. agentcentral hosts the Amazon Seller MCP server. Header-capable clients use https://mcp.agentcentral.to/mcp with an Authorization bearer key.

What Amazon Seller Central data and actions are exposed?+

agentcentral exposes scoped tools for Amazon Ads, inventory, orders, catalog, ranking, finance, and fulfillment data. Supported write tools can be enabled for ads, catalog, price, inventory quantity, and fulfillment operations, but keys can also stay read-only.

How is agentcentral different from a raw Amazon API wrapper?+

A raw API wrapper leaves the client to handle Amazon OAuth, report queues, pagination, joins, history, and permissions. agentcentral connects Amazon once, normalizes seller data into an account-isolated layer, then exposes scoped MCP tools with retained history and audit logs.

Can agents compare current Amazon data to last year?+

Yes, where retained history exists. agentcentral keeps synced seller history while the account is active, so an agent can compare current windows to prior periods or year-over-year without rebuilding exports. New accounts should not assume unlimited historical backfill.

What should sellers compare across Amazon MCP servers?+

Compare whether the MCP server is hosted or local, which Amazon data domains it exposes, whether it supports Claude and ChatGPT, how it handles auth, data latency, scoped keys, and write auditing. agentcentral is a hosted option documented at https://agentcentral.to/amazon-seller-central-mcp.

Can one AI agent query Amazon inventory and ads together?+

Yes. agentcentral exposes Amazon Ads, inventory, orders, catalog, ranking, finance, and fulfillment data through one hosted MCP server, so an AI client can query ads and inventory data from the same seller-data layer.

Is agentcentral a recommendation engine?+

No. agentcentral is a data layer. It returns seller data, source fields, deterministic metrics, factual classifications, and audited write results. The AI client decides what to do with the data.

Can write tools be disabled?+

Yes. API keys can omit write tools so a Claude, ChatGPT, or custom-agent workflow stays read-only.

Point your AI client at Amazon seller data.

Connect Amazon once and your agent reads ads, inventory, orders, catalog, ranking, finance, and fulfillment through one hosted endpoint. Free for 7 days, no credit card.