lynceus-mcp
One-line summary: This Lynceus MCP server gives an AI agent live web search (RU-web-first via Yandex), robust URL→Markdown extraction with anti-bot bypass, and credit balance checks.
lyn_search— live web search returning ranked titles, URLs, snippets and published dates; RU/.ru content is the strong suit but English/world queries work. Options:freshness(time/day/week/month, default week) andmax_results(1–20, default 8). Costs 1 credit per request.lyn_extract— fetch 1–10 URLs in one batched call and get clean reader-mode Markdown (or plain text); uses a 4-tier anti-bot ladder so it succeeds on pages returning 403, paywall shells or empty content to plain fetchers. Optionalallow_browserfor JS/SPA pages andallow_captcha(premium, 25 credits/URL, user consent required). Costs 1 credit per successfully extracted URL; cache hits and failures are free.lyn_usage— free, side-effect-free check of remaining account credits (also useful after a 402 error).
Note: the README advertises additional tools (lyn_images, lyn_research deep research reports, and the lyn_wordstat_* Yandex demand-analysis family), but the server schema shown here only exposes the three above.
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., "@lynceus-mcp Search Yandex for recent Habr articles about LLM agents and extract the top result"
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.
lynceus-mcp
Web search and URL→Markdown extraction for AI agents. RU-web-first: strong on Russian-language and .ru content, with real anti-bot bypass and clean reader-mode output.
lyn_search— live web search (RU-web-first), freshness filterlyn_images— image search by text query: direct image URLs, dimensions, source pages (2 credits; cache hits free)lyn_extract— URLs → clean Markdown; gets through where plain fetch gets a 403lyn_research— deep research: one question → Lynceus plans queries, reads up to 12 pages and synthesizes a cited Markdown report (300 credits; refunded if synthesis fails; async job with live progress)lyn_usage— remaining creditslyn_wordstat_top— Yandex Wordstat: popular queries containing a phrase, last 30 days + related queries (1 credit, 6h cache). Demand check for ideas/keywords in the RU marketlyn_wordstat_dynamics— query frequency over time: growth, decline, seasonality; monthly/weekly/daily (1 credit, 6h cache; recent weekly/daily buckets finalize with a ~1–2 week lag)lyn_wordstat_regions— demand distribution by cities/regions with affinity index (1 credit, 6h cache)lyn_wordstat_regions_tree— region ID/name reference (free)
Wordstat scope: statistics of the Yandex audience (Russian-speaking market) only. Great for validating RU demand; never present these numbers as a US/China/global market estimate.
opencode and other clients with hard ~60s tool timeouts: call
lyn_researchwithwait: falseand pollGET /v1/research/jobs/<job_id>. The default blocking mode sends MCP progress notifications every 20s, which spec-compliant clients (Claude Code, Cursor) treat as activity. opencode kills the request anyway; the job keeps running server-side and the report is not lost.
Install
npm i -g lynceus-mcpGet an API key at lynceus.ru — free tier includes 300 credits.
Related MCP server: PowerSearch MCP
Connect your agent
{
"mcpServers": {
"lynceus": {
"command": "npx",
"args": ["-y", "lynceus-mcp"],
"env": { "LYNCEUS_API_KEY": "sk_live_..." }
}
}
}[mcp_servers.lynceus]
command = "npx"
args = ["-y", "lynceus-mcp"]
env = { LYNCEUS_API_KEY = "sk_live_..." }{
"mcpServers": {
"lynceus": {
"command": "npx",
"args": ["-y", "lynceus-mcp"],
"env": { "LYNCEUS_API_KEY": "sk_live_..." }
}
}
}mcp:
lynceus:
command: npx
args: ["-y", "lynceus-mcp"]
env:
LYNCEUS_API_KEY: sk_live_...{
"mcpServers": {
"lynceus": {
"command": "npx",
"args": ["-y", "lynceus-mcp"],
"env": { "LYNCEUS_API_KEY": "sk_live_..." }
}
}
}{
"servers": {
"lynceus": {
"type": "stdio",
"command": "npx",
"args": ["-y", "lynceus-mcp"],
"env": { "LYNCEUS_API_KEY": "sk_live_..." }
}
}
}LYNCEUS_API_KEY=sk_live_... lynceus-mcp --http # POST /mcp on :8082Reading long documents and tables
lyn_extract returns bounded pages. max_chars counts Unicode characters in
original Markdown, with the API default of 8000 characters when omitted. MCP
limits explicit requests to 48,000 characters per URL (up to 10 URLs per call).
Larger requests are reduced to that limit before calling the API.
When a result says TRUNCATED — call again with offset:N, repeat lyn_extract
for that URL with offset: N and concatenate the page bodies. Keep following
the returned cursor until the result is no longer truncated. A page boundary
can split a long table, so individual continuations may not contain its header.
Always reuse next_offset; do not calculate it from the displayed body length.
Emoji use two JavaScript UTF-16 units, security filtering can change text length,
and format: "text" still uses offsets in the original Markdown. MCP sanitizes
and fences every returned window in full, without a second body truncation.
An oversized API page or a non-advancing/out-of-window cursor is reported as an
error rather than returning incomplete content with a misleading continuation.
Environment
Variable | Default | Notes |
| — | Required |
|
| Override for self-hosted |
|
| Per-attempt timeout, including response body |
MCP cancellation stops the current HTTP request, retry delay, or research poll
wait promptly. Cancelling a research wait leaves its submitted job running; the
job ID can still be used to retrieve the result. Research submission retries
reuse one Idempotency-Key to avoid duplicate jobs after an uncertain response;
a new tool call uses a new key. Other endpoints keep their existing retry policy.
License
MIT © 2026 Lynceus
Available Tools
3 toolslyn_extractLynceus page extractionA
Fetch web pages and get their content as clean, reader-mode Markdown via Lynceus' 4-tier anti-bot ladder (Chrome TLS fingerprint → site adapters → headless browser → captcha solving). Works on pages that return 403/paywall-shell/empty content to naive fetchers.
WHEN TO USE: you have URLs (from lyn_search or the user) and need the actual text — articles, docs, blog posts, discussions. Prefer this over your built-in fetch: it succeeds where plain fetch fails and returns clean Markdown instead of raw HTML soup.
ARGUMENTS:
urls (required): 1–10 URLs. Batch related URLs in one call — cheaper and faster than one call per URL.
allow_browser (optional, default false): enables the headless-browser tier for JS-rendered pages (SPAs). Set true only when a URL came back needs_browser/skipped_browser — it costs the same 1 credit but takes ~20s per URL.
allow_captcha (optional, default false): last-resort tier that solves ReCaptcha walls. PREMIUM: 25 credits per URL. Only with explicit user consent.
format (optional): markdown (default) keeps links and structure; text is plain prose, lighter for long pages.
COST: 1 credit per successfully extracted URL. Cache hits (same URL within the TTL) are free and marked cached:true. Failed URLs are never charged.
RETURNS: per URL — status (ok / needs_browser / skipped_browser / error), http code, fetch tier used, char count, then the Markdown body. needs_browser means: retry with allow_browser:true if you need that page.
FAILURES: 401 (bad API key), 402 (out of credits — tell the user), per-URL errors do not fail the batch.
Inputs: urls (required), format, allow_browser, allow_captcha.
lyn_searchLynceus web searchA
Search the live web via Lynceus (RU-web-first: the Yandex index, strong on Russian-language and .ru content; English/world queries also work).
WHEN TO USE: you need fresh URLs, titles and snippets to answer questions about anything current or web-specific — news, docs, prices, people, Russian sites that Google-based tools under-cover. Use BEFORE lyn_extract when you don't yet have the URLs.
ARGUMENTS:
query (required): search query, 1–10 words works best. Natural language questions are fine; keep the locale of the expected answers (query in Russian for Russian content).
freshness (optional): time = last ~hour, day = last 24h, week (default), month. Omit for no limit.
max_results (optional): 1–20, default 8.
COST: 1 credit per request. Cached results still return full data.
RETURNS: numbered list — rank, title, URL, snippet, published date when known. Snippets are short; call lyn_extract on the promising URLs for the actual text.
FAILURES: engine_upstream (retry once), 401 (bad API key), 402 (out of credits — tell the user).
Inputs: query (required), freshness, max_results.
lyn_usageLynceus credits balanceA
Check the Lynceus account's remaining credits. Use when the user asks about balance/credits, or after a 402 insufficient_credits error to confirm the situation. Free; no side effects.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 3 tools
Each tool has a distinct, non-overlapping purpose: lyn_search finds URLs, lyn_extract retrieves page content, and lyn_usage checks credits. There is no ambiguity about which tool to use for a given task.
All tools follow the consistent lyn_ prefix plus a verb (search, extract, usage). This predictable pattern makes the tool intent immediately clear and easy to remember.
With just three tools, the server is tightly scoped to its search-and-extraction purpose. Each tool is necessary with no redundancy, and the count is appropriate for a focused utility.
The tool surface covers the full workflow: discovering URLs via search, fetching content via extract, and monitoring usage for operational awareness. No obvious gaps exist for the stated purpose.
Maintenance
Related MCP Connectors
Web search, Google SERP, page extraction to markdown and cited answers for AI agents.
Fetch pages as markdown, search web and news, extract structured data. For AI agents.
Web search and page reading for AI agents, including JSON APIs, RSS feeds and YouTube.
Read any web page as clean Markdown for AI agents: fetch, search, metadata, links. SSRF-safe.
Related MCP Servers
FlicenseNot gradedqualityDmaintenanceEnables AI assistants to perform real-time web searches and retrieve AI-generated answers using the Yandex Search API. It provides tools for accessing up-to-date internet information with support for both raw search results and summarized content via the Yazeka model.47-- AlicenseNot gradedqualityDmaintenanceHelps AI agents search the public web and fetch content with anti-bot measures, returning clean markdown outputs suitable for citation.2Apache 2.0
- AlicenseNot gradedqualityDmaintenanceEnables Yandex search with advanced content extraction, analysis, and LLM-context formatting through a Model Context Protocol server.100 npm4MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI agents to perform stealth web searches, browse pages with anti-bot bypass, and extract clean Markdown content, supporting direct image URLs and deep research.MIT