Provides tools for searching the web using Yandex Cloud Search API, with configurable query, result count, search type, and region.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@yandex-search-api Search for Yandex Cloud Search API documentation"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Cloud Function tool for AI Studio MCP Hub. It exposes search_web, calls
Yandex Cloud Search API v2, decodes rawData, and returns compact JSON results.
cd search-mcp-deploy
export SEARCH_API_FOLDER_ID="<folder-id>"
export SEARCH_API_API_KEY="<service-account-api-key>"
./deploy_search_mcp.shThe service account behind the API key needs search-api.webSearch.user on the
folder. By default the function stays private for AI Studio MCP Hub invocation.
Credentials are not stored in this repository; pass them only through
environment variables.
Related MCP server: yandex-searchapi-mcp
Tool Type: Cloud Functions
Server Name: yandex-search-api
Tool Name: search_web
Function: search-api-mcp
Instruction: Ищи актуальную информацию через Yandex Cloud Search API. На вход принимает query, max_results, search_type, region.
{
"query": "Yandex Cloud Search API",
"max_results": 3,
"search_type": "SEARCH_TYPE_RU",
"region": "225"
}This server cannot be deployed
Yandex search results, images, and SERP data via the Apify Yandex Search Scraper, hosted MCP.
DuckDuckGo search as JSON. Ranked results, ads in their own array, 37 regions.
Web search, page reading and structured extraction for AI agents, with strong RU coverage
Live web search, image search, topic filters and full-text fetch over our own crawled index.
