Canonical page: https://www.kuudo.com/features/amazon-vendor-central-mcp/ Built directly on the official Selling Partner API # The Amazon Vendor Central API, run by your AI agents. The Amazon Vendor Central API is the vendor side of Amazon's Selling Partner API (SP-API): purchase orders, shipments, invoices, direct fulfillment, Retail Analytics and Data Kiosk. This MCP server is built directly on it. Authorize it against your own Vendor Central account and those operations are tools your AI calls from ChatGPT, Claude, Cursor or any MCP client. Choose [Managed MCP](/managed-mcp/), which Kuudo hosts and operates, or run it in your own [Private Cloud](/features/cloud-platforms/). [Explore the private beta](/contact/) [Read the docs](/docs/) mcp · vendor · 11 packages vendor-orders vpo\_ vendor-shipments vshp\_ vendor-invoices vinv\_ vendor-transaction-status vts\_ df-orders dfo\_ region: NA · EU · APAC auth: vendor-scoped · LWA 11 packages · NA + EU + FE · operated by your AI What your agents can do ## Every Vendor Central operation, now something your AI just does. Every Vendor Central function — from procurement to analytics — is now a job your AI runs for you, not a click in the portal. Whatever your operation needs done as a vendor, your agents handle it directly. vpo\_\* MCP tools vendor-orders ### Retail Procurement Orders Your AI acknowledges POs, handles cancellations and change orders, and keeps procurement moving on its own. vshp\_\* MCP tools vendor-shipments ### Retail Procurement Shipments Submit shipment requests, retrieve labels, and confirm shipments through your AI — every artifact handled in one workflow. vinv\_\* MCP tools vendor-invoices ### Retail Procurement Invoices Invoices and credit notes filed by your AI — never double-filed, safe to retry, and audit-clean against the POs you received. vts\_\* MCP tools vendor-transaction-status ### Retail Procurement Transaction Status Your AI reconciles every acknowledgement, shipment request, and invoice — every recovery window watched as it happens. dfo\_\* MCP tools df-orders ### Direct Fulfillment Orders Your AI pulls DF orders, acknowledges them, and keeps state in sync — fulfillment moves while your team focuses on growth. dfs\_\* MCP tools df-shipping ### Direct Fulfillment Shipping Shipping labels, container labels, packing slips, customer invoices, and shipment confirmations — every artifact your AI needs to ship on time. dfi\_\* MCP tools df-inventory ### Direct Fulfillment Inventory Inventory updates posted by your AI with the right bill-to address every time — your DF warehouses stay accurate in real time. dfp\_\* MCP tools df-payments ### Direct Fulfillment Payments DF invoices submitted and reconciled by your AI — payment status closes itself against shipped orders. dft\_\* MCP tools df-transactions ### Direct Fulfillment Transactions Track DF transaction status across order, shipping, inventory, and payment workflows — one AI view, every event. dk\_\* MCP tools data-kiosk ### Data Kiosk Run Data Kiosk analytics queries through your AI — the waiting and polling handled for you, analytics on the dashboard the same day. reports\_\* MCP tools vendor-retail-analytics ### Vendor Retail Analytics Sales, traffic, inventory, forecasting, and net pure margin — every legacy report including real-time variants, available to your AI agents. Vendor Central and shared Selling Partner services covered Vendor DF Orders Vendor DF Shipping Vendor DF Inventory Vendor DF Payments Vendor DF Transaction Status Vendor DF Sandbox Test Data Vendor Retail Procurement Orders Vendor Retail Procurement Shipments Vendor Retail Procurement Invoices Vendor Retail Procurement Transaction Status Data Kiosk (GraphQL) Vendor Sales Report Vendor Traffic Report Vendor Inventory Report Vendor Forecasting Report Net Pure Product Margin Rapid Retail Analytics — Sales Rapid Retail Analytics — Traffic Rapid Retail Analytics — Inventory Real-time Sales Report Real-time Traffic Report Real-time Inventory Report Brand Analytics — Market Basket Brand Analytics — Search Terms Brand Analytics — Repeat Purchase Promotion Performance Coupon Performance A+ Content Catalog Items Listings Items Product Type Definitions Notifications (DETAIL\_PAGE\_TRAFFIC\_EVENT, ITEM\_INVENTORY\_EVENT\_CHANGE, ITEM\_SALES\_EVENT\_CHANGE) Tokens Uploads Repository and registry [github.com/KuudoAI/amazon-vendor-central-mcp](https://github.com/KuudoAI/amazon-vendor-central-mcp) [MCP Registry: io.github.KuudoAI/amazon-vendor-central-mcp](https://registry.modelcontextprotocol.io/v0.1/servers?search=io.github.KuudoAI%2Famazon-vendor-central-mcp&version=latest) / context budget ## Amazon's tool definitions total 3,794 tokens. Kuudo's total 478. Vendor Central uses the same SP-API stack. This shared benchmark was measured on Selling Partner endpoints, not vendor-specific tools.A smaller entry point leaves more context for the task. These totals measure each connector's full entry-point definitions. Clients such as Claude can load those definitions on demand, so the total is not necessarily paid at connection. [How it was measured](#sp-context-budget-method). Full entry-point definitions Amazon's official SP connector 8 tools Largest definition: 1,127 tokens 3,794tokens 11.86% of a 32k window 1.9% of a 200k window Kuudo Selling Partner MCP 3 tools Largest definition: 192 tokens 478tokens 1.49% of a 32k window 0.24% of a 200k window Each cell is 32 tokens. Every tool is drawn at its measured size, largest first. 87.4% smaller entry-point definition footprint Kuudo searches a prepared catalog locally, then loads the operation detail your agent needs. The catalog can grow without loading every operation into the conversation. Measurement method and scope Measured 2026-10-22 with cl100k\_base. Counts include name, description and input schema, serialized as compact sorted JSON. They exclude conversation history, server instructions and protocol wrappers. Amazon's definitions were transcribed from Claude's view, with its client-added name prefix removed. The platform may transform text. Kuudo's definitions were captured directly from its authenticated MCP endpoint. Both connectors expose operation discovery. Claude also deferred Amazon's entry-point definitions in the measured session. This comparison measures their full definition footprint, not actual opening-context usage or billed tokens. Measured 2026-10-22 · cl100k\_base / schema size ## 47 matched schemas. 48.1% fewer tokens with Kuudo. Shared SP-API benchmark: these matched schemas cover seller operations, not vendor-specific purchase orders or invoices.Across 47 matched operations, Amazon's full definitions total 37,817 tokens; Kuudo's total 19,637. Both sides include the tool name, description and full input schema. These are the combined sizes of the measured set, loaded only when requested. [How it was measured](#sp-schema-budget-method). Full definitions · 47 matched operations Amazon's official SP connector 47 schemas Largest definition: 1,629 tokens 37,817tokens 18.91% of a 200k window 3.78% of a 1M window Kuudo Selling Partner MCP 47 schemas Largest definition: 1,576 tokens 19,637tokens 9.82% of a 200k window 1.96% of a 1M window Each cell is 200 tokens. Every tool is drawn at its measured size, largest first. 48.1% fewer tokens across the matched full definitions Kuudo returns a compact parameter summary by default. The full input schema is available when your agent needs more detail. The comparison above uses the full definitions on both sides. Measurement method and scope Measured 2026-10-22 with cl100k\_base, using the same fields and serialization as the entry-point comparison. Each operation is counted separately. The totals are not a typical task or session cost. The matched operations share their operation-name suffixes, top-level business parameter names and required business parameters. Amazon adds entityId and toolVersion. Nested constraints and execution equivalence were not tested; shorter descriptions and different schema detail contribute to the totals. Amazon's schema results were transcribed from Claude's view; Kuudo's full schemas were captured directly. The two analytics metric tools and monthEndClosing had no exact match and were excluded. No seller operations were executed. Measured 2026-10-22 · cl100k\_base Regions & markets ## Twenty-two Amazon marketplaces. One conversation. Acknowledge POs across all 16 EU markets in one prompt. Compare sell-through in Japan and the US side by side. Switch markets without switching tools. Regions & markets Every Amazon marketplace where you sell — connected at once 22 markets - 3 regions North America 4 * 🇨🇦Canada * 🇺🇸United States * 🇲🇽Mexico * 🇧🇷Brazil Asia-Pacific 2 * 🇦🇺Australia * 🇯🇵Japan Europe (EU region) 16 * 🇮🇪Ireland * 🇪🇸Spain * 🇬🇧United Kingdom * 🇫🇷France * 🇧🇪Belgium * 🇳🇱Netherlands * 🇩🇪Germany * 🇮🇹Italy * 🇸🇪Sweden * 🇿🇦South Africa * 🇵🇱Poland * 🇪🇬Egypt * 🇸🇦Saudi Arabia * 🇹🇷Turkey * 🇦🇪U.A.E. * 🇮🇳India Global footprint Every Amazon marketplace has its own quirks — different permissions, different regions, different rules. Kuudo handles the wiring so your chat just asks the right one. Where it fits ## Four ways to run Vendor Central without the portal. ### AI agents for brand operations Your brand team asks Claude or ChatGPT to acknowledge POs, confirm shipments, file invoices, or pull yesterday's sales — without anyone opening the Vendor Central portal. ### Multi-brand agency desks One place for every vendor code — the right marketplace every time, each code's access kept to itself, and the same workflow across every brand your agency manages. ### Consulting and operator engagements Stand up Vendor Central operations for a new client in days, not months. Same MCP, new vendor code, same AI workflows on day one. ### Real-time analytics for brand and category teams Build sales, traffic, inventory, and forecasting dashboards on Data Kiosk and Rapid Retail Analytics — the same MCP your agents use in production. Coverage ## One server. Wired into chat, code, workflow, and IDE. Conversational - End-user top SP campaigns last 7d? mcp - ads - query\_campaigns chatgpt - claude - gemini ![ChatGPT logo](/assets/images/chat/chatgpt.svg) ![Claude logo](/assets/images/chat/claude-color.svg) ![Claude Desktop logo](/assets/images/chat/claude-color.svg) ![Gemini logo](/assets/images/chat/gemini-color.svg) ![Perplexity logo](/assets/images/chat/perplexity-color.svg) ### Chat assistants Connect Kuudo as an MCP server inside the chat your team already uses. Ask for campaigns, listings, or reports in plain language. Answers come back grounded in live Amazon data. [ChatGPT OpenAI](/docs/quick-start/chatgpt/) [Claude Anthropic](/docs/quick-start/claude-ai/) [Claude Desktop Native MCP](/docs/quick-start/claude-ai/) Gemini Google [Perplexity Answer engine](/docs/quick-start/perplexity/) Autonomous - Long-running planok list\_campaigns42 pause\_underperformers7 report\-> ![OpenCode logo](/assets/images/code/opencode-light.svg) ![OpenCode logo](/assets/images/code/opencode-dark.svg) ![Hermes logo](/assets/images/workflow/hermesagent-light.svg) ![Hermes logo](/assets/images/workflow/hermesagent-dark.svg) ![Goose logo](/assets/images/workflow/goose-light.svg) ![Goose logo](/assets/images/workflow/goose-dark.svg) ![Continue logo](/assets/images/ai/mcp-light.svg) ![Continue logo](/assets/images/ai/mcp-dark.svg) ![OpenClaw logo](/assets/images/workflow/openclaw-color.svg) ![NanoClaw logo](/assets/images/workflow/nanoclaw.svg) ### Agentic task runners Run multi-step goals against Amazon's APIs. Lean, efficient tools keep agents moving, so they finish the job instead of running out of room. OpenCode Open-source [Hermes Agent runtime](/docs/quick-start/hermes/) Goose Block Continue OSS [OpenClaw Agent runtime](/docs/quick-start/openclaw/) [NanoClaw Containerized agent](/docs/quick-start/nanoclaw/) Triggers - Scheduled jobs trigger cron - 1h \-> mcp Kuudo.ads n8n make ap agent ![n8n logo](/assets/images/workflow/n8n.svg) ![Activepieces logo](/assets/images/workflow/activepieces.svg) ![Make logo](/assets/images/workflow/make-color.svg) ![OpenAI Agent Builder logo](/assets/images/ai/openai-light.svg) ![OpenAI Agent Builder logo](/assets/images/ai/openai-dark.svg) ### Workflow and automation Drop Kuudo tools into the visual workflow builder you already operate. Trigger campaign updates, listing fixes, and report exports on a schedule or from any upstream event. [n8n Self-host](/docs/quick-start/n8n/) [Activepieces OSS](/docs/quick-start/activepieces/) Make iPaaS OpenAI Agent Builder Hosted IDE - Terminal $ claude mcp add Kuudo connected - 21 tools $ cursor @Kuudo list\_orders cursor - codex - claude code - antigravity ![Claude Code logo](/assets/images/code/claudecode-color.svg) ![Codex logo](/assets/images/code/codex-color.svg) ![Cursor logo](/assets/images/code/cursor-light.svg) ![Cursor logo](/assets/images/code/cursor-dark.svg) ![Antigravity logo](/assets/images/code/antigravity-color.svg) ![Lovable logo](/assets/images/code/lovable-color.svg) ### Coding and dev environments Wire Amazon data into the loop your engineers already use. Build dashboards, debug listings, and prototype agents without leaving the editor. [Claude Code Anthropic](/docs/quick-start/claude-code-mcp/) [Codex OpenAI](/docs/quick-start/codex/) [Cursor IDE](/docs/quick-start/cursor/) [Antigravity Google](/docs/quick-start/antigravity/) [Lovable App builder](/docs/quick-start/lovable/) Choose your deployment ## The same Kuudo. Your choice of deployment. Your AI, your knowledge, your rules. Choose Managed MCP for velocity or Private Cloud for infrastructure control. Start with either and move between them. ### Managed MCP Kuudo operates the MCP services. Connect your accounts and use the AI client your team already works in. [Explore Managed MCP →](/managed-mcp/) [Set up Amazon Vendor Central MCP](/docs/managed-mcp/vendor-central/) ### Private Cloud Run Kuudo in your own cloud account, with control of the infrastructure. Agent Flow adds pipelines and a lake in your storage. [Explore Private Cloud →](/features/cloud-platforms/) [Choose or change your deployment](/docs/deployment-choice/) ### Connect it in three steps 1. 1Choose Managed MCP or Private Cloud above. Obtain the service URL and authentication details for that connection, and authorize the Amazon account you want to use. 2. 2Add the service to your client with its connection details: as a custom MCP server in ChatGPT, a custom connector in Claude, or with `claude mcp add` in Claude Code. Follow the setup guide for your deployment and client. 3. 3Ask a read-only question about the accounts or marketplaces you can reach. Name the account and marketplace before asking the AI to work. Start with [Managed MCP setup](/docs/managed-mcp/) or your Private Cloud connection details, then follow your client's connection reference: [ChatGPT](/docs/quick-start/how-to-connect-amazon-vendor-central-to-chatgpt/), [Claude](/docs/quick-start/how-to-connect-amazon-vendor-central-to-claude/) and [Claude Code](/docs/quick-start/claude-code-mcp/). Guides ## Playbooks built on this surface Real operator workflows, grounded in Amazon Agent Atlas, that run through this product. [ Vendor Central · Retail Analytics 6 min ### Amazon Vendor Central Catalog: Find Data Gaps Audit the Amazon Vendor Central catalog for missing ASINs and attribute mismatches, then route each finding to the right correction or suppo... ](/guides/vendor-ara-catalog-quality/)[ Vendor Central · Operations 7 min ### Amazon Shortage Claims: Reconcile and Dispute Reconcile Amazon shortage claims against invoice, PO, shipment and receipt records, then prepare the evidence for a Vendor Central dispute. ](/guides/amazon-shortage-claims/)[ Vendor Central · Operations 8 min ### Amazon Direct Fulfillment: From Order to Shipment Amazon Direct Fulfillment sends a vendor order straight to the customer. Follow the order, inventory, shipment and exception checks that kee... ](/guides/amazon-direct-fulfillment/)[ Vendor Central · Operations 12 min ### Amazon Vendor Central EDI: Set It Up or Use the API Amazon Vendor Central EDI is optional: the Selling Partner API also handles purchase orders, ASNs and invoices. See which route fits each pr... ](/guides/amazon-vendor-central-edi/)[ Vendor Central · Retail Analytics 9 min ### Amazon Retail Analytics API: ARA to Your Warehouse Use the Amazon Retail Analytics API to load ARA sales, inventory, traffic, forecast and Net PPM reports into a warehouse that matches Vendor... ](/guides/vendor-retail-analytics-api-warehouse/)[ Vendor Central · Operations 8 min ### How to Prevent Amazon Vendor Chargebacks Amazon vendor chargebacks follow published clocks and thresholds. Check each purchase order decision against them before you submit, not aft... ](/guides/vendor-operational-performance-chargebacks/)[ Vendor Central · Operations 11 min ### Vendor Central vs Seller Central for Hybrid Brands Vendor Central vs Seller Central: in Vendor Central you sell to Amazon at a cost price it approves; in Seller Central you sell to customers... ](/guides/vendor-central-vs-seller-central/)[ Vendor Central · Retail Analytics 11 min ### Amazon Glance Views and Conversion Rate Explained Read Amazon glance views and conversion rate beside matching sales and inventory reports to separate traffic, units per view, and availabili... ](/guides/vendor-ara-traffic-dashboard/)[ Vendor Central · Retail Analytics 12 min ### Amazon P70 Forecast: Build a Vendor Production Plan Use an Amazon P70 forecast within an explicit forecast policy. Align weekly demand to production lead time, then net stock and committed sup... ](/guides/vendor-ara-demand-forecast/)[ Vendor Central · Retail Analytics 19 min ### Amazon Vendor Inventory Health: Rank by Cost Rank Amazon vendor inventory health by unhealthy inventory cost, then aged sellable stock, with the ARA report's condition and view kept exp... ](/guides/vendor-ara-inventory-health/)[ Vendor Central · Retail Analytics 12 min ### Amazon Retail Analytics Sales: Compare Views Reconcile Amazon Retail Analytics sales by view and reporting clock. Compare ordered and shipped revenue, returns, and the matching SP-API r... ](/guides/vendor-ara-sales-dashboard/)[ Vendor Central · Operations 9 min ### Amazon A+ Content Rejected: Triage the Cause Amazon A+ content rejected? Sort listing, asset, eligibility, and no-fix conditions across affected ASINs before repairing and resubmitting... ](/guides/vendor-aplus-error-resolution/)[ Vendor Central · Operations 12 min ### Amazon A+ Content Automation: Preflight and Patch Use Amazon A+ content automation to scan documents and applied ASINs, check listing data and assets, patch failures, and hold submissions fo... ](/guides/vendor-aplus-content-automation/)[ Vendor Central · Operations 12 min ### Automate Amazon Vendor Listing Quality Checks Audit Amazon vendor listing quality across a catalog: prioritize ASINs, resolve product type schemas, and propose validated writes for polic... ](/guides/vendor-listing-quality-automation/)[ Vendor Central · Operations 10 min ### Fix an Amazon A+ Content ASIN Error Before Writing Diagnose an Amazon A+ content ASIN error through the barcode, brand string, and product type before writing modules or starting another revi... ](/guides/vendor-catalog-data-preflight/)[ Vendor Central · Retail Analytics 10 min ### Amazon Retail Analytics Metrics and Report Types Read Amazon Retail Analytics metrics by dashboard and SP-API report: Sourceable Product OOS, ROOS, glance views, conversion, sales, and fore... ](/guides/vendor-ara-reports-metric-glossary/)[ Vendor Central · Operations 12 min ### Amazon Net PPM Analysis: Find ASIN Margin Leakage Use Amazon Net PPM analysis to rank ASIN margin deterioration and separate cost, funding, and discount pressure where the report exposes tho... ](/guides/vendor-net-ppm-margin-leakage/)[ Vendor Central · Operations 9 min ### Dispute Amazon PO On-Time Accuracy Chargebacks Build an Amazon PO on-time accuracy chargeback dispute with matching PO or carrier evidence, the correct filing route, and the 30-day deadli... ](/guides/vendor-po-chargeback-disputes/) [Vendor Central Operations Guides](/guides/vendor-ops/) [Amazon Retail Analytics Guides](/guides/vendor-analytics/) Frequently asked questions ## Common questions. What is the Amazon Vendor Central API? + The vendor side of Amazon's Selling Partner API (SP-API). Amazon describes it as web service integration between Amazon and vendors for automating retail and direct fulfillment trading relationships, usable instead of EDI or alongside an existing EDI setup. This MCP server is built directly on it. How does a vendor get Amazon Vendor Central API access? + A direct integration means registering a developer profile, creating the AWS resources and an SP-API application, requesting the roles that gate each operation, developing and testing against Amazon's sandbox, then releasing and maintaining it. With this MCP server the vendor authorizes access to its own Vendor Central account and the operations are already tools your AI can call. What does the Vendor Central MCP handle? + Purchase order acknowledgements, cancellations and change orders, shipment requests and labels, invoices and transaction status, direct fulfillment orders, and the retail analytics reporting. Can I automate Vendor Central purchase orders and catalog management? + Yes. Purchase order acknowledgements, shipments and invoices run through the Amazon Vendor Central MCP, and catalog work runs through the Selling Partner API operations vendors also use: Catalog Items, Listings Items and A+ Content, reached through the shared Selling Partner tools. One AI client works across both, with writes guarded by your policy. Why does this matter more for vendors than sellers? + Vendor Central runs on deadlines you cannot miss. PO acknowledgements before the OTIF penalty, shipment confirmations before the truck leaves, reports before the call has already been made. Does it work across several vendor codes? + Yes. It is built for brands, agencies running many vendor codes, and consultants standing up new clients, rather than assuming a single account. Can I manage Vendor Central and Seller Central accounts together? + Yes. A brand that sells to Amazon as a vendor and on Amazon as a seller connects the Amazon Vendor Central MCP and the Amazon Selling Partner MCP side by side. One AI client then works across purchase orders, shipments and Retail Analytics on the vendor side and orders, inventory and listings on the seller side, with advertising alongside through the Amazon Ads MCP. Can Kuudo automate Amazon PPC for a vendor with a large catalog? + Yes. Vendors advertise through the same Amazon Ads API, so the Amazon Ads MCP runs their campaigns, and the Vendor Central MCP puts purchase orders and Retail Analytics beside them. Skills audit campaign structure and pace budgets across the catalog, and each change stays a proposal until it is approved. Which regions are supported? + North America, Europe, and the Far East. Access is vendor-scoped and authenticated with Login with Amazon. Is direct fulfillment included? + Yes. Direct fulfillment orders, shipping, and inventory sit alongside the retail procurement packages. Can agents write in Vendor Central, or only read? + Both, within the scope of the credentials you grant. Reads change nothing; a write, such as acknowledging a purchase order, applies your workspace policy first, which can require a person to approve it. The bottom line ## Your AI runs Vendor Central. You still run the business. It acknowledges the PO before the penalty, confirms the shipment, files the invoice, checks it was accepted, pulls yesterday's sales — across every marketplace, around the clock. You set the limits and make the calls that matter. Brands grow without hiring more analysts. Agencies run more vendor codes without the context-switching. Consultants stand up a new client in days, not months. [Explore the private beta](/contact/) [How Kuudo is built for production](/features/) [See Amazon Agent Atlas](/features/agent-atlas/) [MCP overview](/features/mcp/) [Security & auth docs](/docs/)