Query Yandex Webmaster indexing, queries, diagnostics and backlinks, and recrawl, via an AI agent.
Copy the AI prompt to install this server into Claude Code, Cursor, or another agent β or use 1-click editor setup below.
π‘ Paste into ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows)
Ask your Yandex Webmaster data in plain language β from Claude, Cursor, or any MCP client.
Read-only by design (plus URL recrawl), no secrets stored. Sign in with a built-in public OAuth client over PKCE β no app registration, no client secret.
Early development (v0.1). The tool surface is still growing.
A Model Context Protocol server that exposes Yandex Webmaster as a small set of
flexible, well-described tools instead of one-thin-wrapper-per-endpoint. Pairs
with yandex-metrica-mcp:
run both and an agent can cross-reference search queries from Webmaster with
on-site behavior and conversions from Metrica in a single conversation.
1. Add the server to your MCP client (Claude Desktop, Cursor, β¦):
2. Sign in β interactive, no secret needed:
Approve access in the browser, paste the code Yandex shows you. The token is
cached at ~/.config/yandex-webmaster-mcp/token.json (mode 0600).
3. Ask your agent β e.g. "List my Webmaster hosts and show the SQI for example.com."
Existing community servers tend to be thin wrappers β one tool per API endpoint, dumping raw JSON into the model's context. This server aims to be well-engineered: fewer, smarter tools; compact, structured output; read-only by default so an agent can explore your Webmaster data safely.
get_hosts β list the sites available to your token with their host_id,
URL and verification state; optionally a host summary (SQI, indexed/excluded
pages, site problems). Read-only. Call this first.search_queries β search-query analytics from Yandex Search: impressions,
clicks, average show/click position. report="top" ranks the queries bringing
the most traffic; report="trend" returns a time series (per query or the
site aggregate). Filter by device and date range. Read-only.get_indexing β how Yandex crawls and indexes the host. report="history"
gives crawled pages by HTTP status class over time; report="crawled" lists
example crawled URLs with their codes; report="in_search" lists example pages
currently in search. Read-only.get_diagnostics β problems detected on the site (DNS, slow response,
robots.txt, 4xx, β¦) with severity, active problems first. Read-only.list_sitemaps β the Sitemap files Yandex knows, with URL counts, error
counts and where each was discovered. Read-only.get_external_links β inbound links (backlinks): report="samples" for
example links with source/target, report="history" for the count over time.
Read-only.recrawl_status β remaining daily recrawl quota plus recent recrawl tasks
and their state; pass taskId to check one task. Read-only.recrawl_submit β ask Yandex to recrawl a specific URL sooner. The one
write tool; consumes one unit of the daily quota. Returns the task id.Planned: write tools for sitemaps, original texts and feeds, deferred to a later, opt-in release.
Three ways, in priority order:
npx @boxlab/yandex-webmaster-mcp auth.
Uses the built-in public OAuth client over PKCE; the token is valid ~6 months.YANDEX_WEBMASTER_TOKEN (e.g. for CI) to an OAuth
token for an app with the webmaster:hostinfo scope.YANDEX_OAUTH_CLIENT_ID (and
YANDEX_OAUTH_CLIENT_SECRET to enable automatic token refresh). The app needs
the webmaster:hostinfo and webmaster:verify scopes.See .env.example for all configuration.
Bun-first:
The published package runs on Node; local development uses Bun.
MIT
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
[](https://allmcps.com/mcp/yandex-webmaster-mcp)<a href="https://allmcps.com/mcp/yandex-webmaster-mcp"><img src="https://allmcps.com/api/badge/yandex-webmaster-mcp?style=directory" alt="Yandex Webmaster Mcp on AllMCPs" /></a>