The Yandex Search MCP Server acts as a powerful set of "eyes" for AI assistants, allowing models like Claude or Cursor to browse the live web. Instead of relying solely on their training data, which might be outdated, this tool gives AI agents the ability to look up real-time information, news, and facts across the internet. It bridges the gap between static AI knowledge and the ever-changing digital world, ensuring that the answers provided are as current as possible. Under the hood, this server provides two primary tools that developers can leverage depending on the specific needs of their agent. The `web_search_post` tool delivers traditional search results complete with source links, which is perfect for verification and deep research. For more immediate synthesis, the `ai_search_post` tool utilizes the Yandex Yazeka AI model to process search results and return a concise, generated answer directly to the assistant. This allows an AI agent to not just find links, but to understand and summarize current events in a single step. For developers and power users, the server offers flexible integration options via the Model Context Protocol, supporting both remote SSE connections and local deployments using Docker or Python. It is designed for enterprise-grade stability, requiring a Yandex Search API key and a specific Folder ID with configured permissions to ensure secure access. By implementing this server, developers can transform a standard LLM into an autonomous agent capable of executing complex web-based tasks, while maintaining granular control over the search region and data retrieval through a standardized, extensible interface.
Category: AI & LLM Tooling
Tags: information-retrieval, real-time, web search, yandex
Visit Yandex Search MCP Server
npx. Local Installation If you prefer to run the server locally, clone the repository and install dependencies: bash git clone https://github.com/yandex/yandex-search-mcp-server.git cd yandex-search-mcp-server * For Python: pip install -r requirements.txt * For Docker: docker build -t yandex-mcp-server-image:latest . ---yc.search-api.execute scope) and a Folder ID (with search-api.editor role).claude_desktop_config.json: json { "mcpServers": { "yandexSearch": { "command": "npx", "args": [ "-y", "mcp-remote", "https://d5dj4o5pbnqgca1d546v.cmxivbes.apigw.yandexcloud.net:3000/sse", "--header", "ApiKey:<your_api_key>", "--header", "FolderId:<your_folder_id>" ] } } }sse * URL: https://d5dj4o5pbnqgca1d546v.cmxivbes.apigw.yandexcloud.net:3000/sse json { "mcpServers": { "yandexSearch": { "type": "sse", "url": "https://d5dj4o5pbnqgca1d546v.cmxivbes.apigw.yandexcloud.net:3000/sse", "headers": { "ApiKey": "<your_api_key>", "FolderId": "<your_folder_id>" } } } }json { "mcpServers": { "yandex-search-api": { "autoApprove": [], "disabled": false, "timeout": 60, "type": "stdio", "command": "env", "args": [ "SEARCH_API_KEY=<your_api_key>", "FOLDER_ID=<your_folder_id>", "python3", "/path/to/yandex-search-mcp-server/server.py" ] } } } ---json { "query": "Who won the most recent Formula 1 race in 2025?", "search_region": "en" }web_search_post to find the new SDK documentation and suggests the correct updated code based on the search results.ai_search_post tool uses the Yandex Yazeka AI model to search the web and generate a single, coherent answer based on the most relevant results. This provides a "Perplexity-like" experience directly within Claude or other MCP-compatible clients. Example: A user asks Claude, "What were the key highlights of the international technology forum held yesterday?" Claude calls the ai_search_post tool, searches the latest news, and provides a summarized bullet-point list of events with the relevant context.web_search_post tool, an AI agent can perform deep searches across the web and return not just the information, but the specific source URLs. This allows the user to click through to the primary source for further validation. Example: An analyst tells their AI assistant, "Find the top 5 emerging fintech startups in the CIS region and provide links to their official websites and recent funding news." The MCP fetches the data and presents a table with the company name, a brief description, and the verified source link for each entry.Part of MCP Servers