Yandex Search

v1.0.0Search & Data Extractionstable

Enables AI assistants to perform real-time web searches and retrieve AI-generated answers using the Yandex Search API. It provides tools for accessing up-to-date internet information with support for both raw search results and summarized content via

yandex-searchmcpai-integration
Share:
38
Stars
0
Downloads
0
Weekly
0/5

What is Yandex Search?

Yandex Search is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables ai assistants to perform real-time web searches and retrieve ai-generated answers using the yandex search api. it provides tools for accessing up-to-date internet information with support for ...

Enables AI assistants to perform real-time web searches and retrieve AI-generated answers using the Yandex Search API. It provides tools for accessing up-to-date internet information with support for both raw search results and summarized content via

This server falls under the Search & Data Extraction category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Enables AI assistants to perform real-time web searches and

Use Cases

Search the web in real-time and retrieve AI-generated answers using Yandex Search API integration.
yandex

Maintainer

LicenseNOASSERTION
Languagepython
Versionv1.0.0
UpdatedMay 20, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx yandex-search

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Yandex Search

The Yandex Search MCP Server enables AI assistants to perform real-time web searches using the Yandex Search API, returning either raw search results with sources or AI-generated summarized answers powered by the Yandex Yazeka model. It provides two distinct tools — a standard web search and an AI-synthesized answer search — making it especially useful for Russian-language queries or scenarios where Yandex's index provides better coverage than Western search engines. Developers and users who need up-to-date internet information injected into their AI workflows will find this a lightweight Python-based integration.

Prerequisites

  • Python 3.8+ installed
  • A Yandex Cloud account with Search API access enabled
  • A Yandex Search API key with scope `yc.search-api.execute`
  • A Yandex Cloud Folder ID (service account must have `search-api.editor` role)
  • Claude Desktop or another MCP-compatible AI client
1

Clone the repository and install dependencies

Clone the official Yandex Search MCP server repository and install the Python dependencies listed in requirements.txt.

git clone https://github.com/yandex/yandex-search-mcp-server.git
cd yandex-search-mcp-server
pip install -r requirements.txt
2

Obtain a Yandex Search API key and Folder ID

Log in to Yandex Cloud (console.yandex.cloud), navigate to Search API, and create a service account with the `search-api.editor` role. Generate an API key with the `yc.search-api.execute` scope and note your Folder ID from the cloud console.

3

Set environment variables

Export the two required environment variables before starting the server. These authenticate your requests to the Yandex Search API.

export SEARCH_API_KEY="your-yandex-search-api-key"
export FOLDER_ID="your-yandex-folder-id"
4

Configure Claude Desktop to run the server

Edit your claude_desktop_config.json to add the Yandex Search MCP server, passing your API key and Folder ID as environment variables.

{
  "mcpServers": {
    "yandex-search": {
      "command": "python",
      "args": ["/path/to/yandex-search-mcp-server/server.py"],
      "env": {
        "SEARCH_API_KEY": "your-yandex-search-api-key",
        "FOLDER_ID": "your-yandex-folder-id"
      }
    }
  }
}
5

Test the search tools

Restart Claude Desktop and ask it to search the web. Two tools are available: `web_search_post` for raw results with sources, and `ai_search_post` for AI-generated answers from Yandex Yazeka.

Yandex Search Examples

Client configuration

Full claude_desktop_config.json entry for the Yandex Search MCP server with required credentials.

{
  "mcpServers": {
    "yandex-search": {
      "command": "python",
      "args": ["/path/to/yandex-search-mcp-server/server.py"],
      "env": {
        "SEARCH_API_KEY": "your-yandex-search-api-key",
        "FOLDER_ID": "your-yandex-folder-id"
      }
    }
  }
}

Prompts to try

These prompts use the web_search_post and ai_search_post tools exposed by the server:

- "Search the web for the latest news about the Russian tech industry"
- "Use AI search to get a summary of quantum computing breakthroughs in 2025"
- "Find recent articles about Yandex's new AI models"
- "Search for current weather conditions in Moscow"
- "What are the top programming languages trending in Eastern Europe right now?"

Troubleshooting Yandex Search

API returns 403 Forbidden

Verify your `SEARCH_API_KEY` has the `yc.search-api.execute` scope and that your service account has the `search-api.editor` role for the specified `FOLDER_ID`. Check the Yandex Cloud IAM settings.

Server starts but returns no results

Confirm `FOLDER_ID` matches the folder where Search API is enabled in your Yandex Cloud project. The Folder ID is visible in the Yandex Cloud console URL when viewing your project.

Python import errors on startup

Ensure you installed dependencies with `pip install -r requirements.txt` in the same Python environment used to run the server. Consider using a virtual environment to isolate dependencies.

Frequently Asked Questions about Yandex Search

What is Yandex Search?

Yandex Search is a Model Context Protocol (MCP) server that enables ai assistants to perform real-time web searches and retrieve ai-generated answers using the yandex search api. it provides tools for accessing up-to-date internet information with support for both raw search results and summarized content via It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Yandex Search?

Follow the installation instructions on the Yandex Search GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Yandex Search?

Yandex Search works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Yandex Search free to use?

Yes, Yandex Search is open source and available under the NOASSERTION license. You can use it freely in both personal and commercial projects.

Browse More Search & Data Extraction MCP Servers

Explore all search & data extraction servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "yandex-search": { "command": "npx", "args": ["-y", "yandex-search"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Yandex Search?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides