{
  "markdown": "# Amazon Seller MCP Server - DataDoe\n\n> **Hosted Amazon Seller Central & Vendor Central MCP server with read and write access.** Connect Claude, ChatGPT, Cursor, Codex, Gemini, and GitHub Copilot to live Amazon SP-API and Amazon Ads API data, then let your AI agent act on it: update listings, manage orders, and optimize Amazon Ads campaigns. DataDoe handles the SP-API developer approval, OAuth, and rate limits so your AI agent starts working in under a minute.\n\n[![Amazon Seller & Vendor](https://img.shields.io/badge/Amazon-Seller%20%26%20Vendor-FF9900?style=flat-square)](https://www.datadoe.com/)\n[![SP-API Selling Partner API](https://img.shields.io/badge/SP--API-Selling%20Partner-FF6F00?style=flat-square)](https://developer-docs.amazon.com/sp-api/)\n[![Amazon Ads API](https://img.shields.io/badge/Amazon-Ads%20API-232F3E?style=flat-square)](https://advertising.amazon.com/API/docs)\n[![MCP Server](https://img.shields.io/badge/MCP-Model%20Context%20Protocol-8A2BE2?style=flat-square)](https://modelcontextprotocol.io/)\n[![Read and Write](https://img.shields.io/badge/Amazon-Read%20%2B%20Write-2EA043?style=flat-square)](#actions-write-to-amazon)\n[![AI clients supported](https://img.shields.io/badge/AI%20clients-20%2B%20guides-D97757?style=flat-square)](#quick-setup-per-ai-client)\n[![smithery badge](https://smithery.ai/badge/jakopv007/datadoe-mcp)](https://smithery.ai/servers/jakopv007/datadoe-mcp)\n[![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg?style=flat-square)](LICENSE)\n\n🔗 [Start a free trial](https://www.datadoe.com/connect/amazon/mcp) · 📘 [Documentation](https://www.datadoe.com/hub/docs) · ⚡ [Actions](https://www.datadoe.com/hub/docs/datadoe-features/actions) · 📊 [Amazon data schema](https://www.datadoe.com/hub/data-scheme) · 🎥 [Video demo](https://www.youtube.com/watch?v=9YQd7M2dMyY)\n\n---\n\n## 🚀 Quick start\n\n1. Sign up at [DataDoe](https://www.datadoe.com/connect/amazon/mcp) and connect your Amazon Seller Central or Vendor Central account.\n2. Create a DataDoe MCP API key in [DataDoe MCP Integrations](https://app.datadoe.com/integrations/mcp).\n3. Paste the config below into your AI client (Claude, Cursor, Codex, Gemini, GitHub Copilot, ChatGPT, or any MCP-capable tool):\n\n   ```json\n   {\n     \"mcpServers\": {\n       \"datadoe\": {\n         \"url\": \"https://mcp.datadoe.com/mcp/v1\",\n         \"headers\": {\n           \"datadoe-mcp-key\": \"<YOUR_DATADOE_MCP_KEY>\"\n         }\n       }\n     }\n   }\n   ```\n\n4. Ask your AI agent: *\"Show my top 10 ASINs by revenue last month across all Amazon marketplaces.\"*\n\nThat's it. DataDoe runs the MCP server on hosted infrastructure, so your team doesn't need to deploy anything locally or wait for Amazon SP-API developer approval.\n\n---\n\n## What is DataDoe MCP?\n\n**DataDoe MCP** is a hosted [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server for **Amazon sellers, vendors, and agencies**. It exposes your live Amazon Selling Partner API (SP-API) and Amazon Ads API data through MCP tools that work with Claude, ChatGPT, Cursor, Codex CLI, Gemini CLI, GitHub Copilot, Claude Desktop, n8n, NanoClaw, and any other MCP-capable client.\n\nDataDoe MCP gives your AI agent two layers over your Amazon account:\n\n- **A read layer** - SKU-level orders, sales, ads spend, traffic, inventory, listings, returns, settlements, brand analytics, and catalog, returned as structured tool responses or downloadable CSV and JSON exports.\n- **A write layer (Actions)** - your agent can change your Amazon account through the SP-API and Amazon Ads API: update listings, cancel orders, confirm shipments, and manage Amazon Ads campaigns, ad groups, targets, and ads.\n\nBuilding your own Amazon SP-API integration typically requires SP-API developer registration, OAuth refresh-token flow, marketplace-specific endpoints, throttling logic, and 2-4 weeks of Amazon approval. DataDoe takes care of all of that. You get a single authenticated MCP URL for both reading and acting on your Amazon data.\n\n![DataDoe MCP - Amazon Seller Central, Vendor Central, and Amazon Ads data for AI agents via SP-API](/assets/datadoe-mcp-banner.png)\n\n## Who is DataDoe MCP for?\n\n- **Amazon sellers (FBA, FBM, multi-marketplace)** - get instant answers from your own seller data without context-switching to Seller Central.\n- **Amazon agencies** managing multiple client accounts - query across every connected Seller Central / Vendor Central account from one MCP server.\n- **Vendors with Vendor Central** - read 1P data alongside 3P data with the same tools.\n- **AI builders and developers** - ship Amazon-aware AI agents, dashboards, and internal tools without writing your own SP-API integration.\n- **Operations teams** - automate recurring reports via Claude Code, Cursor, n8n, or any MCP-capable workflow tool.\n\n## Why use DataDoe MCP?\n\n- ✅ **No SP-API approval needed** - DataDoe handles SP-API developer registration, OAuth, refresh tokens, and rate limits on your behalf.\n- ✅ **30-second setup** - paste the MCP URL and your API key into your AI client config. DataDoe runs the server on hosted infrastructure.\n- ✅ **20+ documented integrations** out of the box: Claude, ChatGPT, Cursor, Codex, Gemini CLI, GitHub Copilot, n8n, CrewAI, the Claude & OpenAI Agent SDKs, Excel / Word / PowerPoint via Claude, and any other MCP-capable client.\n- ✅ **SKU-level resolution** - drill into individual ASINs, parent listings, marketplaces, time periods, ad campaigns, keyword reports, settlements, returns.\n- ✅ **Multi-marketplace, multi-account** - one MCP server covers every Amazon marketplace (US, UK, DE, FR, IT, ES, CA, AU, JP, MX, and more) across Seller Central and Vendor Central.\n- ✅ **AI-native by design** - `exports_create` accepts SQL-like filter groups, GROUP BY, aggregations, and date intervals, so your AI agent can build complex reports from one tool call.\n- ✅ **Read and write** - with [Actions](#actions-write-to-amazon), your agent doesn't just report, it updates listings, manages orders, and optimizes Amazon Ads, with a `dryRun` validation step and per-type controls.\n- ✅ **Always-on hosted infrastructure** - DataDoe manages SP-API rate limits, token rotation, and ongoing maintenance.\n\n## What can you ask DataDoe MCP?\n\nExample questions your AI agent can answer with DataDoe MCP connected:\n\n- *\"What were my top 20 ASINs by revenue last month across all Amazon marketplaces?\"*\n- *\"Reconcile my Amazon settlements against orders for Q1, and show any discrepancies.\"*\n- *\"Which Amazon Ads campaigns had ACoS over 40% last week, and what was their total spend?\"*\n- *\"Show inventory units at risk of stocking out in the next 14 days.\"*\n- *\"Build me a daily KPI dashboard with sales, traffic, and ad spend for the last 90 days.\"*\n- *\"Which search terms in my PPC reports drove the most clicks but zero conversions?\"*\n- *\"Pull every Amazon return for SKU ABC-123 in the last 60 days and summarize the return reasons.\"*\n- *\"Compare my brand analytics search term share-of-voice month over month.\"*\n\nAnd with **Actions** enabled, your agent can act on what it finds:\n\n- *\"Raise the daily budget on my top-ACoS Sponsored Products campaign by 20%.\"*\n- *\"Pause every campaign with ACoS over 50% last week.\"*\n- *\"Update the price of SKU ABC-123 to 19.99 and refresh its bullet points.\"*\n- *\"Confirm shipment for order 123-4567890-1234567 with UPS tracking 1Z999...\"*\n\n## Actions: write to Amazon\n\nActions let your AI agent make changes on your connected Amazon Seller Central, Vendor Central, and Amazon Ads accounts through the SP-API and Amazon Ads API. Every Action is recorded and auditable.\n\nWhat your agent can do:\n\n- **Listings** - update the title, bullet points, description, price, generic keyword, and item-type keyword (`AMAZON_LISTINGS_UPDATE`).\n- **Orders** - cancel an order item with a reason (`AMAZON_ORDERS_CANCEL`) or confirm shipment and upload tracking (`AMAZON_ORDERS_CONFIRM_SHIPMENT`).\n- **Amazon Ads** - add, update, remove, and find campaigns, ad groups, targets, ads, and ad associations across Sponsored Products, Brands, Display, TV, and Amazon DSP.\n\nHow it works - the agent runs each Action through these MCP tools:\n\n1. `actions_details_schema_get` - get the payload schema for the Action type.\n2. `actions_start` with `dryRun=true` - validate the payload without executing.\n3. `actions_start` - run the Action and get an action id.\n4. `actions_get` - poll until it completes, then read the `result`.\n\nUse `actions_list` to review past Actions (filter by status, type, creator, and date).\n\nAction types are disabled by default and enabled per type in [Settings > Actions](https://app.datadoe.com/settings?tab=actions). When a type is disabled, `actions_start` rejects live runs but still allows `dryRun` validation.\n\nExample `details` payload for `AMAZON_LISTINGS_UPDATE`:\n\n```json\n{\n  \"type\": \"AMAZON_LISTINGS_UPDATE\",\n  \"sellerOrVendorId\": \"<SELLER_OR_VENDOR_UUID>\",\n  \"dryRun\": true,\n  \"details\": {\n    \"changes\": [\n      {\n        \"sku\": \"ABC-123\",\n        \"language_tag\": \"en_US\",\n        \"name\": \"Stainless Steel Water Bottle 750ml\",\n        \"price\": 19.99\n      }\n    ]\n  }\n}\n```\n\nRunning an Action costs 2 AI tokens for up to 100 entities, plus 1 token per additional 100. See the [Actions docs](https://www.datadoe.com/hub/docs/datadoe-features/actions) for the full catalog and payload schemas.\n\n## Available MCP tools\n\nDataDoe MCP exposes the following tools to your AI client:\n\n| Tool | Category | What it does |\n|---|---|---|\n| `sellers_and_vendors_list` | Account | Lists Amazon sellers and vendors connected to your DataDoe organization, with pagination and optional filters by name and marketplace country code. |\n| `organization_and_subscription_details_get` | Account | Returns your DataDoe organization profile and active subscription plan. |\n| `exports_sources_get` | Data | Searches DataDoe's catalog of pre-built Amazon data export templates (orders, sales and traffic, ads performance, inventory, listings, settlements, returns, brand analytics, and more). |\n| `exports_create` | Data | Creates an Amazon data export from any source. Supports SQL-like filters, GROUP BY, aggregations (sum / avg / count / countDistinct / min / max), date intervals (DAY / WEEK / MONTH), pagination, and CSV or JSON output. |\n| `exports_get` | Data | Returns status and metadata for an in-flight or completed export job. |\n| `exports_list` | Data | Lists export jobs for the organization with pagination and optional export ID filters. |\n| `exports_raw_url_get` | Data | Returns a one-time download URL served by the DataDoe MCP server for a completed export. |\n| `exports_raw_download` | Data | Returns the raw export content (CSV or JSON) inline in the tool response. |\n| `exports_delete` | Data | Deletes an export by its ID. |\n| `files_create` | Files | Creates and uploads a utility file (listing or A+ images) as base64-encoded content. |\n| `files_list` | Files | Lists utility files for the organization with pagination and filters. |\n| `files_get` | Files | Returns metadata for a utility file by id. |\n| `files_download_url_get` | Files | Returns a one-time download URL for an uploaded file. |\n| `files_delete` | Files | Deletes a utility file and its stored object when present. |\n| `datadoe_user_docs_table_of_contents_get` | Docs | Returns the table of contents of the DataDoe user documentation, useful when an agent needs to look up features or capabilities on demand. |\n| `datadoe_user_docs_page_get` | Docs | Returns the full content of a named DataDoe documentation page. |\n| `actions_details_schema_get` | Actions | Returns the JSON Schema of the `details` payload required to start a given Action type. |\n| `actions_start` | Actions | Starts an Action that changes your Amazon account (listings, orders, Amazon Ads). Set `dryRun=true` to validate without executing. Returns an action id. |\n| `actions_get` | Actions | Returns the status and `result` of an Action by id; poll after `actions_start`. |\n| `actions_list` | Actions | Returns paginated Action history, filterable by status, type, creator, and date. |\n| `cogs_upsert` | COGS | Creates or updates cost-of-goods-sold rows for a seller or vendor. |\n| `cogs_delete` | COGS | Deletes COGS rows for a seller or vendor with optional filters. |\n| `vendor_code_upsert` | Vendor codes | Creates or updates vendor code rows for a seller or vendor. |\n| `vendor_code_delete` | Vendor codes | Deletes vendor code rows for a seller or vendor with optional filters. |\n| `plugins_get` | Plugins | Returns enabled DataDoe Plugins (Memories, Skills, and Files) for the user. |\n| `plugins_memories_create` | Plugins | Creates a memory Plugin for the user or organization. |\n| `plugins_memories_edit` | Plugins | Updates a memory Plugin for the user or organization. |\n| `plugins_skills_get` | Plugins | Returns a Skill element (SKILL.md or supporting file) listed by plugins_get. |\n| `plugins_files_get` | Plugins | Returns converted markdown content for a File plugin listed by plugins_get. |\n\n---\n\n## Quick setup per AI client\n\nThe snippets below are the minimum config you need. For step-by-step guides per AI client, see the [Per-client setup guides](#per-client-setup-guides) list at the end of this section.\n\n### Claude Desktop · Claude.ai\n\n```json\n{\n  \"mcpServers\": {\n    \"datadoe\": {\n      \"url\": \"https://mcp.datadoe.com/mcp/v1\",\n      \"headers\": {\n        \"datadoe-mcp-key\": \"<YOUR_DATADOE_MCP_KEY>\"\n      }\n    }\n  }\n}\n```\n\n### Claude Code\n\n```bash\nclaude mcp add datadoe \\\n  --transport http \\\n  --url https://mcp.datadoe.com/mcp/v1 \\\n  --header \"datadoe-mcp-key: <YOUR_DATADOE_MCP_KEY>\"\n```\n\n### Cursor\n\nAdd to `~/.cursor/mcp.json` (global) or `.cursor/mcp.json` (per project):\n\n```json\n{\n  \"mcpServers\": {\n    \"datadoe\": {\n      \"url\": \"https://mcp.datadoe.com/mcp/v1\",\n      \"headers\": {\n        \"datadoe-mcp-key\": \"<YOUR_DATADOE_MCP_KEY>\"\n      }\n    }\n  }\n}\n```\n\n### GitHub Copilot (VS Code)\n\nAdd to your VS Code `mcp.json`:\n\n```json\n{\n  \"mcpServers\": {\n    \"datadoe\": {\n      \"url\": \"https://mcp.datadoe.com/mcp/v1\",\n      \"headers\": {\n        \"datadoe-mcp-key\": \"<YOUR_DATADOE_MCP_KEY>\"\n      }\n    }\n  }\n}\n```\n\n### Codex CLI · Gemini CLI · ChatGPT · n8n · NanoClaw · any other MCP client\n\nDataDoe MCP works as a **generic remote MCP server**. Configure your client with:\n\n- **URL**: `https://mcp.datadoe.com/mcp/v1`\n- **Transport**: HTTP Streamable\n- **Auth header**: `datadoe-mcp-key: <YOUR_DATADOE_MCP_KEY>` (create a key in [DataDoe MCP Integrations](https://app.datadoe.com/integrations/mcp))\n\n### Per-client setup guides\n\nFor step-by-step setup guides per AI client, see the dedicated DataDoe documentation pages:\n\n- [Using Claude](https://www.datadoe.com/hub/docs/datadoe-mcp/claude)\n- [Using ChatGPT](https://www.datadoe.com/hub/docs/datadoe-mcp/chatgpt)\n- [Using Claude Code](https://www.datadoe.com/hub/docs/datadoe-mcp/claude-code)\n- [Using Claude Agent SDK](https://www.datadoe.com/hub/docs/datadoe-mcp/claude-agents-sdk)\n- [Using Codex](https://www.datadoe.com/hub/docs/datadoe-mcp/codex)\n- [Using Codex Sites](https://www.datadoe.com/hub/docs/datadoe-mcp/codex-sites)\n- [Using CrewAI](https://www.datadoe.com/hub/docs/datadoe-mcp/crewai)\n- [Using Cursor](https://www.datadoe.com/hub/docs/datadoe-mcp/cursor)\n- [Using Excel + Claude](https://www.datadoe.com/hub/docs/datadoe-mcp/excel)\n- [Using Gemini CLI](https://www.datadoe.com/hub/docs/datadoe-mcp/gemini-cli)\n- [Using Gumloop](https://www.datadoe.com/hub/docs/datadoe-mcp/gumloop)\n- [Using Hermes Agent](https://www.datadoe.com/hub/docs/datadoe-mcp/hermes)\n- [Using n8n](https://www.datadoe.com/hub/docs/datadoe-mcp/n8n)\n- [Using NanoClaw](https://www.datadoe.com/hub/docs/datadoe-mcp/nanoclaw)\n- [Using OpenAI Agents SDK](https://www.datadoe.com/hub/docs/datadoe-mcp/openai-agents-sdk)\n- [Using OpenClaw](https://www.datadoe.com/hub/docs/datadoe-mcp/openclaw)\n- [Using OpenCode](https://www.datadoe.com/hub/docs/datadoe-mcp/opencode)\n- [Using PowerPoint + Claude](https://www.datadoe.com/hub/docs/datadoe-mcp/powerpoint)\n- [Using VS Code](https://www.datadoe.com/hub/docs/datadoe-mcp/vs-code)\n- [Using Word + Claude](https://www.datadoe.com/hub/docs/datadoe-mcp/word)\n\nFull documentation root: [www.datadoe.com/hub/docs](https://www.datadoe.com/hub/docs)\n\n---\n\n## What Amazon data is available?\n\nDataDoe MCP exposes every Amazon data table available in DataDoe, including:\n\n- **Orders & sales**: order line items, order performance, sales and traffic, refunds\n- **Amazon Ads**: campaigns, ad groups, keywords, search terms, sponsored products / brands / display, ACoS / ROAS / impression-share metrics\n- **Inventory**: FBA inventory, restock recommendations, stranded inventory, age, units at risk\n- **Listings & catalog**: ASIN catalog, product attributes, buy box ownership, variations\n- **Finance**: settlements, fees, reserves, reimbursements, deposits\n- **Returns**: customer returns, return reasons, FBA returns\n- **Brand analytics**: search query performance, market basket, repeat purchase, demographics\n- **Traffic**: sessions, page views, conversion rate, by ASIN, by marketplace\n\nFull schema: [www.datadoe.com/hub/data-scheme](https://www.datadoe.com/hub/data-scheme)\n\n---\n\n## What DataDoe MCP is NOT\n\nTo avoid confusion when evaluating Amazon MCP servers:\n\n- ❌ **Not a self-hosted MCP server.** DataDoe MCP is hosted at `mcp.datadoe.com`. This GitHub repository is the schema facade used to publish DataDoe MCP to public MCP registries (Official MCP Registry, mcpservers.org, glama.ai, mcpmarket.com, Cline, smithery.ai, and others).\n- ❌ **Not an SP-API wrapper you operate yourself.** DataDoe owns the SP-API developer registration, OAuth flow, refresh-token rotation, marketplace endpoints, and rate-limit handling. You bring your Amazon account; we handle the rest.\n- ❌ **Not a free open-source server.** DataDoe MCP requires a DataDoe subscription. For a free self-hosted alternative, see the community Amazon MCP servers indexed at [mcpservers.org](https://mcpservers.org/).\n\n---\n\n## Documentation & resources\n\n- [DataDoe homepage](https://www.datadoe.com/)\n- [DataDoe documentation](https://www.datadoe.com/hub/docs)\n- [DataDoe Actions (write to Amazon)](https://www.datadoe.com/hub/docs/datadoe-features/actions)\n- [Amazon data schema reference](https://www.datadoe.com/hub/data-scheme)\n- [DataDoe MCP product page](https://www.datadoe.com/connect/amazon/mcp)\n- [DataDoe vs Amazon MCP comparison](https://www.datadoe.com/compare/datadoe-vs-amazon-mcp)\n- [DataDoe MCP video demo](https://www.youtube.com/watch?v=9YQd7M2dMyY)\n- [DataDoe blog: Amazon SP-API, Ads API, and MCP explainers](https://www.datadoe.com/blog)\n- [Create a DataDoe MCP API key](https://app.datadoe.com/integrations/mcp)\n\n---\n\n## License\n\n[MIT](LICENSE). The DataDoe MCP schema facade in this repository is open-source. The hosted MCP server, DataDoe application, and DataDoe infrastructure are proprietary and operated by Deltologic.\n\n---\n\n### How to start and connect locally (for indexing and listing)\n\n> This server is just a schema facade of the actual DataDoe MCP server, made for exposing DataDoe MCP to various MCP registries.\n> It is a no-op server: it does not do anything beyond exposing the schema of DataDoe MCP.\n> If you want to actually use DataDoe MCP, see the [DataDoe MCP documentation](https://www.datadoe.com/hub/docs).\n\n#### 1. Install dependencies\n\n```bash\nyarn install\n```\n\n#### 2. Build the local server\n\n```bash\nyarn build\n```\n\nThis compiles the TypeScript source into `dist/index.js`.\n\n#### 3. Start the server\n\n```bash\nyarn start\n```\n\nThe server communicates over stdio, so the process is intended to be launched by your MCP client rather than opened in a browser.\n\n#### 4. Connect from an MCP client\n\nFor a local setup, point your client at the built entrypoint. A typical `mcp.json` looks like this:\n\n```json\n{\n  \"mcpServers\": {\n    \"datadoe\": {\n      \"command\": \"node\",\n      \"args\": [\"/absolute/path/to/datadoe-mcp/dist/index.js\"]\n    }\n  }\n}\n```\n\nIf your client supports environment-based workspace paths, you can usually swap the absolute path for the actual clone location on your machine.\n\n---\n\nDataDoe is operated by [Deltologic](https://github.com/Deltologic) · [datadoe.com](https://www.datadoe.com/)\n",
  "bytes": 20192,
  "sha": "8a9f9a3054dc8d6f116eeac9bec0f548c371f00c7e8c1217924cacd63aba14b4",
  "repo_slug": "deltologic/datadoe-mcp",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_com_datadoe_amazon_seller_mcp_4cd85f10/readme"
}