Connects AI assistants to Ozon Seller and Performance APIs for multi-store pricing, advertising, orders, finance, and more.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.
💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Inspect callable tools, capabilities, and parameters exposed to AI agents by Ozon MCP Server.
The ozon-mcp-server MCP server exposes Ozon marketplace operations to MCP-compatible AI clients. It covers both the Ozon Seller API and the Performance API, so an assistant can work with catalog data and seller workflows alongside paid advertising. The project is designed for sellers managing multiple stores: calls identify the target shop with a shop_id.
Its 156 tools are organized around common marketplace tasks. These include promotions, discounts, pricing, competitor price indexes, automatic pricing strategies, sponsored-placement campaigns, cost-per-order advertising, products, stock, media, orders, fulfillment, returns, reviews, buyer questions, chats, reports, finance, analytics, ratings, notifications, company details, and store discovery. Diagnostics tools check Ozon API availability and detect degradation.
A local installation communicates over stdio, which suits clients that launch MCP processes directly. The Docker and web installation also provides an SSE endpoint at /sse; clients that do not support SSE directly can use the mcp-remote bridge. The web application includes a dashboard, store management pages, health information, and API diagnostics.
Each configured shop has a handle, display name, and Ozon credentials. Seller API access uses a Client-Id and API key. Performance API access uses a Client-Id and Client-Secret. The server stores shop information, encrypted keys, call statistics, and diagnostic history in its configured data directory. The tool catalog is generated from the server’s tool definitions and is also available through the MCP tools/list method.
For a direct local setup, install the package with uvx ozon-mcp-server or install it with pip and run ozon-mcp. The stdio configuration can provide OZON_CLIENT_ID, OZON_API_KEY, and DATA_DIR. DATA_DIR must point to a writable location; its documented default is /data.
For the browser dashboard, clone the repository, create a .env file from .env.example, and start the Docker Compose deployment. It serves on port 8000 and persists data in the ozon_data volume. Add shops through /shops, where the credentials can be tested with a live Ozon request. Set MCP_AUTH_TOKEN when the service may be reachable by other users. The dashboard and installation guides are in Russian, although the supplied JSON configuration is language-neutral.
The ozon-mcp-server MCP server groups its tools into these supported areas:
The available client guides are Russian-only. SSE compatibility varies by client: Claude Desktop and OpenAI Codex CLI require the mcp-remote bridge, while Zed support is unconfirmed and the bridge is recommended. Ozon credentials and API availability still determine which operations succeed. The repository describes the tool as maintained according to the author’s ongoing use rather than a stated support commitment.
Factual signals from GitHub, npm, and our automated checks — not a rating.
No reviews yet — be the first to share how this listing worked for you.
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/ozon-mcp-server)<a href="https://allmcps.com/mcp/ozon-mcp-server"><img src="https://allmcps.com/api/badge/ozon-mcp-server?style=directory" alt="Ozon MCP Server on AllMCPs" /></a>