Kuudo Managed MCP
Connect your AI to Amazon. Kuudo runs the servers.
Add Amazon Ads, Seller Central, Vendor Central, Atlas and Iris to the AI client your team already uses. Your accounts, knowledge and rules stay yours, whichever deployment you choose.
Updated
Yours in Managed MCP and Private Cloud: your AI client, Amazon accounts, knowledge and rules.
Amazon Ads. Campaigns, bids, budgets and reports, on the official Amazon Ads API.
Operations756
One per operation
Seller Central. Listings, pricing, inventory and orders, read live from your seller account.
One SKU
- Listing
- Buyable
- Price
- Featured offer
- Inventory
- Fulfillable
- Orders
- Shipped
Vendor Central. Purchase orders, shipments and invoices, from your vendor account.
- Purchase order
- Acknowledged
- Shipment confirmed
- Invoice submitted
Atlas. Amazon knowledge your agent checks before it answers: 56,381 content indexes.
What triggers a chargeback?
- Amazon Ads & AMC30,249
- Seller Central18,531
- Vendor Central7,601
Answer cited
Iris. Listing images and product video, built from your real product references.
Main image
- Pure-white backgroundChecked
- About 85% product fillChecked
- Full product visibleChecked
Waiting for approval
Amazon coverage
Sponsored Ads, DSP, AMC, Seller Central, Vendor Central. The whole Amazon job, from the AI you want to use.
Amazon Ads API MCP
Every Amazon Ads API in one place — built so agents stop guessing and start shipping.
Sponsored Products, Brands, Display, DSP, AMC, Attribution, Marketing Stream, and reporting behind one interface.
- Errors that tell the agent the fix
- Lean tools — agents keep room to think
- Every marketplace routed automatically
Amazon SP-API MCP
The whole Selling Partner API, run by your agents instead of your team.
Catalog, Listings, Orders, Shipping, Reports, AWD, Finances, Messaging, and seller operations behind one interface.
- Marketplace-aware routing
- Corrective errors for agents
- Broad Selling Partner coverage
Amazon Vendor Central MCP
All of Vendor Central, run by your agents — not your analysts.
Purchase orders, shipments, invoices, vendor analytics, catalog, A+ Content, and Brand Analytics behind one interface.
- Logs in once per vendor
- Direct Fulfillment and procurement tools
- Errors that correct themselves
Amazon Agent Iris
Amazon listing creative for product images and video, grounded in the live catalog instead of a public product page.
Use live catalog and real product references to build, audit, and deliver a listing's complete visual story from your AI assistant.
- Images and video shots from the same product references
- Product fidelity and listing rules checked before handoff
- Approval-gated image publishing; video shot plans ready to finish
Amazon Agent Atlas
The Amazon knowledge your agent didn't have to earn.
A retrieval layer your agent checks before it answers. It indexes Amazon operating knowledge across Ads, Seller Central, and Vendor Central.
- Indexed Amazon corpus, queried in milliseconds
- Citations on every result — the agent shows its work
Amazon Marketing Cloud
Run audience, attribution, incrementality, and signal-enrichment workflows — without writing a single SQL query.
AMC Skills call your AMC instance, DSP seat, and partner signals through MCP.
- Deep campaign findings and journeys
- Bespoke DSP audience activation
- Privacy-safe run logs and approvals
Where it runs
Use the tools your team already trusts. Or pick a new one.
Kuudo plugs into Claude, Claude Cowork, Claude Code, ChatGPT, Cursor, n8n and any MCP client. No lock-in to anyone's chat box.
ChatGPT
Ask for an audience, a report, or a listing fix in plain language. Kuudo runs it against your Amazon data and answers right in the chat.
Claude Desktop
Connect Kuudo as an MCP server and Claude works your Amazon accounts — campaigns, orders, listings — inside the guardrails you set.
OpenClaw
Hand a multi-step Amazon goal to an autonomous agent. It plans, calls the right tools, and stops at your approval gates.
n8n
Drop Kuudo tools into your workflow builder. Trigger campaign updates, report pulls, and listing fixes on a schedule or from any event.
Codex
Pull real Amazon data into the repository you are already working in. Prototype an agent against live campaigns, with one config across the CLI and the IDE extension.
Perplexity
Ask a question and have it answered from your own Amazon accounts — campaign performance, inventory health, listing status — not the public web.
Skills
Start with the job your agent needs to run.
Each Skill packages the workflow, required context, output contract, and safety boundaries for a repeatable Amazon operation.
Create a DSP campaign
Launch an automated Amazon DSP campaign in the right order, with conversion tracking, tactic-specific ad groups, verification reads, and controlled activation.
Amazon Marketing Cloud
Ask in plain English — new-to-brand, ad frequency, customer lifetime value, off-Amazon conversions — and the skill picks from 50+ proven AMC playbooks, writes validated SQL, and returns privacy-safe answers or DSP-ready audiences.
Amazon Ads reporting
Translate familiar v3 report requests or an ad-hoc metric question into a validated Amazon Ads API v1 CreateReport request your AI client can run.
Listing optimizer
Inspect catalog and listing state, ground recommendations in category rules, preview exact changes, and submit listing or A+ updates only after confirmation.
Listing compliance check
Run an Amazon listing compliance check before you list: find the rules and regulators that apply, check ASIN gating, and get a met or unmet checklist.
Product creative
Create, edit, and audit Amazon main, lifestyle, infographic, and detail images against current Seller Central rules before they reach a listing.
14 of 20 Skills work with Managed MCP. The other 6 use Agent Flow, which runs in Private Cloud.
Regions & markets
Twenty-two Amazon marketplaces. One conversation.
Run the same task across every EU marketplace in one prompt. Compare results from Japan and the US side by side. Switch markets without switching tools.
- Canada
- United States
- Mexico
- Brazil
- Australia
- Japan
- Ireland
- Spain
- United Kingdom
- France
- Belgium
- Netherlands
- Germany
- Italy
- Sweden
- South Africa
- Poland
- Egypt
- Saudi Arabia
- Turkey
- U.A.E.
- India
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.
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 setupPrivate 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 Choose or change your deploymentChoose the deployment. Keep the principles.
Managed MCP provides velocity. Private Cloud provides infrastructure control. Both put your AI client, your Amazon accounts and your operating rules at the center. Starting managed preserves your freedom to choose Private Cloud later.
Add a data lake when the work calls for one.
For recurring ingestion, retained account history and analysis over a lake in your storage, use Agent Flow through Private Cloud. That is a separate data capability from connecting your AI client to a managed service.
Frequently asked questions
Common questions.
What changes when I choose Managed MCP?
Which services are available through Managed MCP?
Can I move to Private Cloud later?
Does Managed MCP include an Agent Flow data lake?
Name the services and the AI client you want to use. Access starts with a working session with the Kuudo team.
Request Managed MCP access