OpenSERP 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
- 3 ★ on the repository
- Last commit
- MIT
Extended access
Why this level
- The server sends search queries to OpenSERP, a local instance or the paid cloud
- Fetches and cleans page text from up to 20 links at a time
Install
- Works in
- Services
Manual install
npm install -g @openserp/mcpGlobal install of the npm package.
Access and checks
How we reviewExtended accessThe tool runs code or makes network calls and only reads external data.
- The server sends search queries to OpenSERP, a local instance or the paid cloud
- Fetches and cleans page text from up to 20 links at a time
This is third-party code. Review the repository files before installing.
What it does
The server provides ten tools on top of OpenSERP: regular, mega (across several engines at once), fast and any search, image search, clean text extraction from one URL or up to 20 at a time, checking remaining quota, and listing available engines. Yandex sits alongside Google and Bing among the engines, selected via the engine parameter in a call. Without OPENSERP_API_KEY the server runs in OSS mode against a local instance at localhost:7000; with a key it switches to OpenSERP Cloud.
Who it is for. For developers who want one search MCP server covering several engines including Yandex, with page text extraction for LLMs.
Good fit when
- You need to compare Google, Bing and Yandex results in one request
- You need to batch-extract clean markdown from up to 20 pages to ground an answer
- You are fine with the OpenSERP Cloud plan or running your own OSS instance
Not a fit when
- You only need Yandex: this is a general multi-engine server, not Yandex-specific
- You lack a Cloud key and do not want to run an OSS instance: without one of the two the server will not work
Example request
Compare Google and Yandex results for this SEO keyword and extract text from the top three linksMCP
- Transport
- stdio, http, sse
- Authentication
- key is optional
Environment variables
OPENSERP_API_KEYsecret- OpenSERP Cloud key; without it the server runs in OSS mode
OPENSERP_BASE_URL- A compatible OpenSERP API base URL, if not the default
Limitations
OSS mode requires a separately running OpenSERP instance at localhost:7000, which this server's README does not describe how to set up. Cloud mode is paid, with a key issued at openserp.org. Yandex search depends on how OpenSERP implements that engine on its side; the details are not disclosed in this repository.
How to disable. Remove the openserp entry from mcpServers in your client configuration.
FAQ
Do I need a key for basic use?
No, without OPENSERP_API_KEY the server runs in OSS mode against localhost:7000, but that instance must be set up separately.
Can I search only Yandex?
Yes, pass engine set to Yandex's identifier in the search or image_search tools, or check list_engines for the exact name.
Discussion
No questions or reviews yet.
Related
All Yandex Search toolsYandex 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
SerpentSeek search gateway with 39 providers
SerpentSeek
A self-hosted Go search gateway with an MCP search tool: 39 providers, including the official Yandex Search API v2
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 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 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 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
README in short
The README shows install via npm or npx, OSS and Cloud modes with different environment variables, a list of ten tools, examples comparing engines and geo-fenced search via the region parameter, and configs for Claude Desktop and Cursor in stdio and HTTP modes.