Amazon MCP server for ChatGPT.
ChatGPT can use Amazon seller data through agentcentral, a hosted Amazon MCP server for Amazon Seller Central inventory, Amazon Ads, orders, catalog, ranking, finance, fulfillment, retained history, and optional guarded writes. Connect Amazon once, create a scoped key, and let ChatGPT call the allowed MCP tools.
The same hosted endpoint can also be used from OpenAI API workflows that support remote MCP servers, so custom ChatGPT-powered agents can query the same seller data layer with inventory, ads, and retained history context while the account is active.
Last updated May 20, 2026.
- ChatGPT setup
- Remote MCP server with scoped agentcentral credential
- Endpoint
- https://mcp.agentcentral.to/mcp
- Data domains
- Ads, inventory, orders, catalog, ranking, finance, fulfillment
- Tool count
- 144 domain-scoped tools plus 4 utility tools
- History
- Retained while active for prior-period and year-over-year comparisons where history exists
- Access control
- Read-only, domain-scoped, or selected write tools
- Amazon auth
- OAuth connection from the agentcentral dashboard
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
Seller data ChatGPT can read.
ChatGPT queries factual Amazon seller rows through the hosted tools, then writes the explanation. agentcentral supplies the structured data; the model handles the wording and the summary.
Ads and campaign data
Campaigns, ad groups, keywords, search terms, placements, budgets, TACOS, retained campaign history, and Amazon Ads source fields.
Inventory and order data
FBA inventory, inbound shipments, days of cover, orders, order details, returns, reimbursements, sales summaries, and retained inventory context while active.
Catalog and ranking data
Listing details, listing quality views, A+ Content, reviews, and keyword rank views with changes and search volume.
Finance and fulfillment data
Fees, profitability, settlement economics, MCF shipping previews, MCF orders, tracking, and returns.
Access model
Adding the server in ChatGPT.
Add agentcentral as a custom connector or MCP server in a ChatGPT workflow that supports remote MCP, then point it at the hosted endpoint with a scoped key.
Connect Amazon
Authorize Amazon Ads and Seller Central in the agentcentral dashboard.
Let data sync
agentcentral syncs and prepares seller data for fast repeated reads and prior-period comparisons while your account is active.
Create a scoped key
Choose the domains and write-tool access for the ChatGPT workflow.
Add remote MCP
Use the hosted MCP endpoint in ChatGPT or an OpenAI API workflow that supports remote MCP.
Related pages
Deeper setup and reference material.
Use these pages for setup, tool coverage, and client-specific configuration details.
ChatGPT with Amazon seller data
ChatGPT-specific overview for Amazon Seller Central data, inventory, ads, and setup links.
Open pageChatGPT quickstart
Step-by-step setup for ChatGPT.
Open pageAmazon Seller Central MCP hub
Canonical hosted Amazon Seller MCP overview for Seller Central, Amazon Ads, data coverage, access model, and supported clients.
Open pageAmazon seller MCP servers compared
Comparison page for official Ads MCP, local repos, Seller Central connectors, automation MCPs, and hosted seller data layers.
Open pageAmazon seller data layer
Data-layer overview for ads, inventory, orders, catalog, ranking, finance, and fulfillment.
Open pageAmazon Ads MCP server
Amazon Ads MCP tools for ChatGPT and other MCP clients.
Open pageAmazon Ads MCP server for Claude
Claude-specific Amazon Ads MCP page for the same hosted ads data surface.
Open pageChatGPT connection walkthrough
Hosted MCP connection path from Seller Central to ChatGPT.
Open pageOpenAI config examples
Remote MCP configuration examples for API workflows.
Open pageExample prompts
Questions to put to ChatGPT.
Phrase requests the way you would in a normal ChatGPT chat. Ask for date windows, source fields, and explicit metrics, and the connector returns the rows behind the answer.
FAQ
Common questions.
How do I use ChatGPT with Amazon seller data?+
Use ChatGPT with Amazon seller data by connecting Amazon in agentcentral, creating a scoped MCP key, and adding the hosted endpoint https://mcp.agentcentral.to/mcp to ChatGPT or an OpenAI API workflow.
Can ChatGPT analyze my Amazon Seller Central inventory?+
Yes. With agentcentral connected, ChatGPT can call MCP tools for Amazon Seller Central inventory, days of cover, inbound shipments, sales velocity, listings, orders, and related seller data.
Can ChatGPT access Amazon Ads data?+
Yes. agentcentral exposes Amazon Ads campaign, keyword, search term, budget, TACOS, placement, and related metrics through MCP tools.
Can ChatGPT compare Amazon seller data year over year?+
Yes, where retained history exists. agentcentral keeps seller history available while the account is active, so ChatGPT can compare current windows to prior periods or the same period last year without rebuilding Amazon exports. New accounts should not assume unlimited historical backfill.
Can ChatGPT make Amazon account changes?+
Only if the API key includes supported write tools. Keys can stay read-only for analysis-only ChatGPT workflows.
Where is the full ChatGPT setup page?+
The ChatGPT overview is https://agentcentral.to/amazon-seller-central-chatgpt and the quickstart is https://agentcentral.to/docs/quickstart/chatgpt.
Bring Amazon seller data into ChatGPT.
Connect Amazon once, add the connector to ChatGPT, and ask about ads, inventory, orders, catalog, finance, and fulfillment. Free for 7 days, no credit card.