Discuss with expertTry it for free
© 2026 Direct Cursus Technology L.L.C.

Yandex Cloud guides in AI tools

Written by
Updated at June 26, 2026

Documentation in Markdown format

Yandex Cloud provides its complete documentation in Markdown format, allowing you to use it as context for AI tools in IDEs such as Cursor, Visual Studio Code with GitHub Copilot, Continue, Cline, and other assistants. This ensures your models generate responses based on up-to-date information, utilizing correct service names, CLI and API parameters, and accurate configuration examples.

Docs in Markdown format are available at:
https://md-docs.website.yandexcloud.net/

MCP server for searching though Yandex Cloud documentation

Yandex Cloud Documentation MCP server provides real-time access to official Yandex Cloud documentation through generative search. Connecting this server equips your AI assistants with the documentation_generative_search tool.

You can add this MCP server to any IDE that supports MCP. The server operates without authorization or tokens.

Connection

The Yandex Cloud Documentation MCP server is available via Streamable HTTP transport at:

https://docs.mcp.cloud.yandex.net/mcp

Configuration

MCP server configuration example:

{
  "mcpServers": {
    "yandex-cloud-documentation": {
      "type": "streamableHttp",
      "url": "https://docs.mcp.cloud.yandex.net/mcp"
    }
  }
}

Where:

  • type: Streamable HTTP transport. The possible values are:
    • streamableHttp: In CamelCase format.
    • streamable-http: In kebab-case format.
    • http: Simplified option for clients that support streaming by default.

Connection examples for popular IDEs

SourceCraft Code Assistant supports configuration at two levels: global and project. For remote servers, Code Assistant uses the Streamable HTTP transport, where the type field must be set to streamable-http. For more information, see this Code Assistant guide.

You can edit both global and project-specific MCP configuration files directly from the MCP settings menu in Code Assistant:

  1. Click in the chat's top panel and select MCP servers.

  2. Select the appropriate option:

    • Edit Global MCP: Opens the global file named mcp_settings.json.
    • Edit Project MCP: Opens the project file named .codeassistant/mcp.json. If there is no such file, Code Assistant will create it automatically.

  3. Add the following configuration to the file:

    {
  "mcpServers": {
    "yandex-cloud-documentation": {
      "type": "streamable-http",
      "url": "https://docs.mcp.cloud.yandex.net/mcp"
    }
  }
}

  4. Save the file.

Claude Code supports configuration at two levels: global and project. For remote servers, Claude Code uses HTTP transport. Read more in this Claude Code guide.

  1. Open the .mcp.json file in the project root.

  2. Add the following configuration to the file:

    • Via HTTP transport:

      claude mcp add --transport http yandex-cloud-documentation \
  --scope project \
  https://docs.mcp.cloud.yandex.net/mcp

    • Via JSON configuration:

      {
  "mcpServers": {
    "yandex-cloud-documentation": {
      "type": "http",
      "url": "https://docs.mcp.cloud.yandex.net/mcp"
    }
  }
}

  3. Save the file.

  1. Open the ~/.mcp.json file in you home directory.

  2. Add the following configuration to the file:

    • Via HTTP transport:

      claude mcp add --transport http yandex-cloud-documentation \
  --scope user \
  https://docs.mcp.cloud.yandex.net/mcp

    • Via JSON configuration:

      {
  "mcpServers": {
    "yandex-cloud-documentation": {
      "type": "http",
      "url": "https://docs.mcp.cloud.yandex.net/mcp"
    }
  }
}

  3. Save the file.

Check the connection in one of the following ways:

  • Terminal:

    claude mcp get yandex-cloud-documentation

  • Claude Code UI:

    /mcp

Cursor supports MCP servers via the mcp.json file. You can apply the configuration globally or for a specific project. For more information, see this Cursor guide.

  1. Create the file:

    • In the project root to apply the configuration to a specific project:

      .cursor/mcp.json

    • In your home directory to apply the configuration globally:

      ~/.cursor/mcp.json

  2. Add the following configuration to the file:

    {
  "mcpServers": {
    "yandex-cloud-documentation": {
      "type": "streamableHttp",
      "url": "https://docs.mcp.cloud.yandex.net/mcp"
    }
  }
}

  3. Save the file and restart Cursor or refresh the list of MCP servers in the settings.

Codex supports remote MCP servers via Streamable HTTP. For such a server, you must specify the url field in the configuration. MCP servers are configured in the ~/.codex/config.toml file. For more information, see this Codex guide.

  1. Open the ~/.codex/config.toml file.

  2. Add the following configuration to the file:

    [mcp_servers.yandex-cloud-documentation]
url = "https://docs.mcp.cloud.yandex.net/mcp"
enabled = true

  3. Save the file and restart Codex.

If your Codex version supports adding remote HTTP MCP servers via the CLI, run this command:

codex mcp add yandex-cloud-documentation \
  --url https://docs.mcp.cloud.yandex.net/mcp

Zoo Code supports configuration at two levels: global and project. For remote servers, Zoo Code uses the Streamable HTTP transport, where the type field must be set to streamable-http. Read more in this Zoo Code guide.

You can edit both global and project-specific MCP configuration files directly from the MCP settings menu in Zoo Code:

  1. Click in the chat's top panel.

  2. In the left-hand panel, select MCP Servers.

  3. Select the appropriate option:

    • Edit Global MCP: Opens the global file named mcp_settings.json.
    • Edit Project MCP: Opens the project file named .roo/mcp.json. If there is no such file, Zoo Code will create it automatically.

  4. Add the following configuration to the file:

    {
  "mcpServers": {
    "yandex-cloud-documentation": {
      "type": "streamable-http",
      "url": "https://docs.mcp.cloud.yandex.net/mcp"
    }
  }
}

  5. Save the file.

Client-agnostic configuration

If your MCP client supports JSON configuration with mcpServers, use one of the below connection options.

Clients with streamableHttp

{
  "mcpServers": {
    "yandex-cloud-documentation": {
      "type": "streamableHttp",
      "url": "https://docs.mcp.cloud.yandex.net/mcp"
    }
  }
}

Clients with streamable-http

{
  "mcpServers": {
    "yandex-cloud-documentation": {
      "type": "streamable-http",
      "url": "https://docs.mcp.cloud.yandex.net/mcp"
    }
  }
}

Clients with URL-based transport

{
  "mcpServers": {
    "yandex-cloud-documentation": {
      "url": "https://docs.mcp.cloud.yandex.net/mcp"
    }
  }
}

Testing

After connecting the server, ask your AI assistant to look up information in the Yandex Cloud documentation.

Request examples:

Use the Yandex Cloud guides and explain how to install the YC CLI.

Search the Yandex Cloud docs for instructions on how to configure a Terraform provider.

If the connection is configured correctly, the AI assistant will call the MCP server tool (documentation_generative_search) and return a response based on information retrieved from the Yandex Cloud documentation.

External tools

Context7

Context7 is an MCP server developed by Upstash. It provides AI assistants and code editors with up-to-date guides and code examples for current library versions.

To access the Yandex Cloud documentation, use this Context7 repository. For detailed configuration instructions, see here.

Previous
Management, monitoring, and billing tools