Developer · Local MCP server

Yandex Direct MCP

MCP server for Yandex Direct API: campaigns, ads, keywords, bids, reports. Click.ru or OAuth.

What the MCP Registry states

The entry as published to the official MCP Registry (read 2026-10-04), latest version.

Registry name
io.github.ai-hub-open/yandex-direct-mcp
Version
0.5.0
Status
Active
Category
developer
Transport
stdio (local process)
Package
npm
Published
2026-07-30
Updated
2026-07-30
Publisher
ai-hub-open (GitHub) · 2 servers with pages here
Repository
github.com/ai-hub-open/yandex-direct-mcp
Source
Registry API entry

Packages

RegistryPackageVersionTransportEnvironment variables
npmruntime: bunx@ai-hub-open/yandex-direct-mcp0.5.0stdioCLICK_RU_PROXY, CLICK_RU_TOKEN (secret), CLICK_RU_CLIENT_LOGIN, YANDEX_DIRECT_TOKEN (secret), YANDEX_DIRECT_SANDBOX

How to connect Yandex Direct MCP

Yandex Direct MCP runs locally from a Node.js package published to the npm registry: @ai-hub-open/yandex-direct-mcp version 0.5.0. It speaks MCP over stdio, so the client starts it as a program and talks to it through standard input and output. It needs Node.js; clients usually start it with npx — the usual command is npx -y @ai-hub-open/yandex-direct-mcp@0.5.0; the entry names bunx as the runtime. It reads these environment variables: CLICK_RU_PROXY, CLICK_RU_TOKEN (secret), CLICK_RU_CLIENT_LOGIN, YANDEX_DIRECT_TOKEN (secret) and YANDEX_DIRECT_SANDBOX; set them in the client's configuration for this server.

In the mcpServers JSON format that many desktop and editor MCP clients read, the entry looks like this (placeholders in angle brackets):

{
  "mcpServers": {
    "yandex-direct-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@ai-hub-open/yandex-direct-mcp@0.5.0"
      ],
      "env": {
        "CLICK_RU_PROXY": "<value>",
        "CLICK_RU_TOKEN": "<secret>",
        "CLICK_RU_CLIENT_LOGIN": "<value>",
        "YANDEX_DIRECT_TOKEN": "<secret>",
        "YANDEX_DIRECT_SANDBOX": "<value>"
      }
    }
  }
}

Derived from the registry entry, not tested here. What the server does, and on what terms, is set by its publisher; check its repository or website before giving it access to your accounts or files. How to add an MCP server to an assistant · Before you connect

More from ai-hub-open (GitHub)

ServerRunsEndpoint or package
Vk Ads MCPMCP server for VK Ads API: campaigns, audiences, budgets, stats. Click.ru, token or OAuth.Local · stdionpm: @ai-hub-open/vk-ads-mcp

More developer servers

All 6,250 →
ServerRunsEndpoint or package
YAACMessaging between concurrent AI coding sessions, across clients, over MCP. Zero infrastructure.Local · stdioPyPI: yet-another-agentic-chat
Yaml Ai MCPAI-powered yaml ai MCP server for agents. Supports validate yaml, convert yaml json, lint yaml. By.Local · stdioPyPI: yaml-ai-mcp
Yandex Delivery MCPMCP server for the Yandex Delivery B2B API: express claims, tracking, NDD/pickup-point orders.Local · stdionpm: mcp-yandex-dostavka
Yandex DirectMCP server for Yandex Direct API v5 — campaigns, ads, keywords, bids, audiences.Local · stdioPyPI: mcp-server-yandex-direct
Yandex Direct MCPMCP server for Yandex Direct API v5: manage PPC campaigns, ads, keywords, and statistics.Local · stdionpm: mcp-yandex-direct
Yandex Metrica MCPQuery Yandex Metrica analytics — reports, trends, metadata and raw log exports — via an AI agent.Local · stdionpm: yandex-metrica-mcp
Yandex MetrikaMCP server for Yandex Metrika API — counters, goals, reports, segments, logs.Local · stdioPyPI: mcp-server-yandex-metrika
Yandex Webmaster MCPMCP server for Yandex Webmaster API: indexing, search queries, sitemaps, diagnostics, links.Local · stdionpm: mcp-yandex-webmaster