Yandex and Google search MCP server
web-compass
An MCP web-search and content-extraction server via Yandex and Google on top of SerpAPI, geared toward RU/CIS results
- 1 ★ on the repository
- Last commit
Extended access
Why this level
- Starts a server that searches through SerpAPI with a paid SERPAPI_KEY
- Extracts text from open pages, with no account sign-in and no writes
Install
- Works in
- Services
Manual install
npm run build && npm run start:prodBuild and run the production server; SERPAPI_KEY is needed in .env.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- Starts a server that searches through SerpAPI with a paid SERPAPI_KEY
- Extracts text from open pages, with no account sign-in and no writes
This is third-party code. Review the repository files before installing.
What it does
The server offers five MCP tools, each with a matching REST endpoint: search_yandex searches via Yandex with a Russia or CIS region, search_google searches globally via Google, extract pulls the main readable text from a list of URLs, and search_and_extract_yandex and search_and_extract_google combine search and extraction in one call. Search runs through the third-party SerpAPI service, which returns Yandex and Google results without directly scraping their pages, and content extraction uses the Mozilla Readability engine, the same one behind Firefox Reader Mode. The server runs over streamable-http and connects by URL rather than launching as a local agent process.
Who it is for. For agents that need web search focused on Russian and CIS results alongside global Google search.
Good fit when
- You need Yandex search with a Russia or CIS region choice
- You want search and readable-text extraction combined in one call
- You are fine relying on the paid third-party SerpAPI service instead of direct scraping
Not a fit when
- You do not want to pay for a SerpAPI key: search does not work without one
- You need a local stdio server rather than a streamable-http URL connection
Example request
Search Yandex for the latest central bank rate news and extract the text of the top three articlesMCP
- Transport
- http
- Authentication
- not required
Environment variables
SERPAPI_KEYrequired, secret- A paid third-party SerpAPI key for Yandex and Google search
Limitations
You need a paid SERPAPI_KEY from the third-party SerpAPI service; without it no search tool works. No license is stated. You need to deploy and keep the server running yourself, there is no ready-made public endpoint.
How to disable. Remove the web-compass entry from your MCP client configuration and stop the server process.
FAQ
Does the server scrape Yandex results directly?
No, results come through the third-party SerpAPI service, which itself fetches Yandex and Google data.
Do I need a key to use it?
Yes, without a paid SERPAPI_KEY neither Yandex nor Google search works.
Discussion
No questions or reviews yet.
Related
All Yandex Search toolsOpenSERP MCP server with Yandex search
@openserp/mcp
An MCP server for the OpenSERP search platform: web and image search across several engines including Yandex, plus page text extraction
Yandex Search API v2 MCP server
yandex-search-mcp
A self-hosted MCP for Yandex Search API v2: web, image and generative search across all six Yandex indexes
Yandex search MCP on .NET with AOT compilation
Yandex Search MCP Server (.NET)
A .NET 10 Yandex search MCP server with native AOT compilation, page-to-Markdown conversion and regex search
Yandex search MCP server in TypeScript
yandex-search-mcp
A TypeScript MCP server for the Yandex Search API with its own result parser and tests
Yandex search MCP server with offline install
MCP Search Server
A search MCP server on the Yandex Cloud Search API with a monitoring dashboard, Brave fallback and an offline bundle for air-gapped networks
Yandex Search MCP via browser automation
yandex-search-mcp
An unofficial Playwright-based MCP server that searches Yandex through a browser with authenticated cookies, extracting and ranking page content for an agent
Comparison with similar tools
Cards that share the main search query, and how they differ.
| Tool | Official | Authentication | Repository stars | Main difference |
|---|---|---|---|---|
| Yandex and Google search MCP server (this card) | no | not required | 1 | |
| Yandex Search MCP via browser automation | no | not required | 4 | searches Yandex through a browser with cookies |
| Yandex search MCP server in TypeScript | no | API key | 0 | in TypeScript, with its own results parser |
| Yandex search MCP on .NET with AOT compilation | no | API key | 0 | on .NET with a native AOT build |
README in short
The README explains why RU/CIS via Yandex sits alongside Google, describes the five tools with parameters and their matching REST endpoints, a Claude Desktop config example over streamable-http, how it is built on SerpAPI and Mozilla Readability, and the dev and production run commands.