Amazon Seller Central MCP server.
agentcentral is a hosted Amazon Seller Central MCP server for sellers who want Claude, ChatGPT, and other AI clients to read structured Amazon seller data. It connects Amazon Ads and Seller Central once, syncs the data into tenant-isolated tables, and exposes 91 domain-scoped MCP tools through a remote HTTP endpoint.
Use agentcentral as the factual data layer behind an AI client: ads, inventory, orders, catalog, rankings, finance, and fulfillment data are normalized first, then exposed through scoped MCP tools.
Last updated May 7, 2026.
- Product type
- Hosted remote MCP server for Amazon sellers
- Endpoint
- https://mcp.agentcentral.to/mcp
- Tool count
- 91 domain-scoped tools plus five utility tools
- Data domains
- Ads, inventory, orders, catalog, ranking, finance, fulfillment
- Client support
- Claude, ChatGPT, OpenClaw, 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
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.
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
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
Authorize Amazon Ads and Seller Central with OAuth from the agentcentral dashboard.
Sync and normalize
agentcentral stores seller data in tenant-isolated BigQuery datasets for fast repeated reads.
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
Deeper setup and reference material.
Use these pages for setup, tool coverage, and client-specific configuration details.
Claude Amazon MCP page
Detailed Claude-oriented overview, prompts, setup notes, and FAQ.
Open pageChatGPT Amazon MCP page
ChatGPT-specific connection page and setup links.
Open pageTool reference
Reference docs for ads, inventory, catalog, ranking, finance, and fulfillment tools.
Open pageMCP comparison
Comparison page for hosted Amazon MCP server options.
Open pageFAQ
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 MCP server after the seller connects Amazon with OAuth.
Does agentcentral require a local MCP server?+
No. agentcentral hosts the MCP server. Header-capable clients use https://mcp.agentcentral.to/mcp with an Authorization bearer key.
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.
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.