OpenAPI-driven Wildberries MCP server

Wildberries MCP Server

A local Wildberries Seller API MCP server built from a 279-method OpenAPI catalog, with calls defaulting to dry-run

  • 0 ★ on the repository
  • Last commit
MCP server

Broad access

Why this level

  • The catalog covers write operations on orders, prices and content, reachable through an explicit allow_write flag
  • wb_raw_request allows calling arbitrary endpoints outside the catalog
All reasons and checks
Russian stack

jerardx/wildberries-mcp-server

Install

Services

Manual install

git clone https://github.com/Jerardx/wildberries-mcp-server.git

Clone the repo, then set up a virtual environment and install requirements.txt.

Access and checks

How we review

Broad accessThe tool can change data, run commands or handle secrets.

  • The catalog covers write operations on orders, prices and content, reachable through an explicit allow_write flag
  • wb_raw_request allows calling arbitrary endpoints outside the catalog

This is third-party code. Review the repository files before installing.

What it does

The server is a thin adapter over a shared wb_client.py: auth, rate limits, 429 retry and write protection live in one place, while the MCP layer only exposes tools to the agent. A catalog built from Wildberries OpenAPI specs covers 279 operations across analytics, communications, finance, FBS, DBS, DBW and FBW orders, products, promotion, reports and tariffs, with a known rate limit for every method. The agent first finds the right method via wb_search_methods or a ready wb_get_recipe business recipe, reads its description with wb_describe_method, and calls it with wb_call_method or wb_raw_request. Every call defaults to dry_run, and a real write requires an explicit allow_write.

Who it is for. For developers and sellers who want full Wildberries Seller API coverage with a safe dry-run before a real write.

Good fit when

  • You need the full Wildberries Seller API method catalog with a known rate limit for each one
  • You want the agent to dry-run a call before writing any data
  • You want ready business recipes for sales, stock or FBS orders

Not a fit when

  • You need a packaged release rather than a source install from what the README calls a private repository
  • You only need a handful of operations, not the full 279-method catalog

Example request

Find the Wildberries method for warehouse stock and show its rate limit

MCP

Transport
stdio
Authentication
API key

Environment variables

WILDBERRIES_API required, secret
A Wildberries seller token

Limitations

The README itself calls the repository private, and install is source-only via git clone and a Python virtual environment. No license is stated. Secrets and real business exports are excluded from the repo; you need your own token.

How to disable. Remove the wildberries entry from your MCP client configuration.

FAQ

Can the agent write data to Wildberries right away?

No, calls default to dry_run; a real write needs an explicit allow_write.

How does the agent find the right method among 279?

Via wb_search_methods by description, or via wb_get_recipe with a ready Russian business scenario.

Discussion

No questions or reviews yet.

Russian stack

An MCP server covering all seventeen Wildberries Seller API hosts: sales, stock, product cards, prices, financial reports and reviews

MCP serverBroad access4Repository stars

Wildberries MCP

wildberries-mcp

Russian stack

MCP server for the Wildberries seller API: products, prices, stock, orders, FBS supplies, analytics, reviews and ads

MCP serverBroad access16Repository stars
Russian stack

Wildberries Seller API MCP server using a search and execute scheme: 235 actions instead of 235 separate tools

MCP serverBroad access2Repository stars
Russian stack

Wildberries Seller API MCP server: cards, prices, promotions, ads, orders, supplies, reviews and finance across several stores

MCP serverBroad access8Repository stars

Wildberries MCP search server

Wildberries MCP Server

Russian stack

A lightweight MCP server for searching Wildberries products via its public JSON API: product card, price, reviews with no browser

MCP serverExtended access2Repository stars

Comparison with similar tools

Cards that share the main search query, and how they differ.

ToolOfficialAuthenticationRepository starsMain difference
OpenAPI-driven Wildberries MCP server (this card)noAPI key0
Wildberries MCP server with a CLI and per-section modulesnoAPI key0per-section modules
Wildberries MCP server with plan and confirmnoAPI key1plan then confirm

README in short

The README lists the repo's contents, current coverage of 279 operations and 279 wrapper scripts with zero methods missing a rate limit, install steps via a virtual environment and .env, connecting as an MCP server for a generic client, Claude Desktop, Cursor, Windsurf and Hermes Agent, the list of MCP tools, and a recommended call order for the agent.

README badge

Report a problem