bukvarix-mcp
MCP server that enables keyword research and domain analysis for the Russian search market (Yandex/Google) via the Bukvarix API, exposing tools for keyword searches and domain comparisons.
README
bukvarix-mcp
MCP server for the Bukvarix API — keyword research and domain analysis for the Russian-language search market (Yandex / Google).
Exposes 5 tools that map 1:1 onto Bukvarix's HTTP endpoints, handling percent-encoding, BOM stripping, and error surfacing for you. Works out of the box with the free API key (api_key=free).
Tools
| Tool | Endpoint | Description |
|---|---|---|
bukvarix_keywords |
GET /v1/keywords/ |
Simple keyword search by a single phrase |
bukvarix_mkeywords |
POST /v1/mkeywords/ |
Extended search by a list (up to 100 phrases + 250 exclusions on free) |
bukvarix_site |
GET /v1/site/ |
Keywords for a single domain |
bukvarix_site_cmp |
GET /v1/site_cmp/ |
Compare two domains (intersect / domain1_uniq / domain2_uniq) |
bukvarix_site_mcmp |
POST /v1/site_mcmp/ |
Compare 3–10 domains |
Common parameters
q— phrase, domain, or newline-separated listq2— second domain, or exclusion list (formkeywords/site_cmp)num— row count (default 250, max 1,000,000 on free)format—json(default) /txt/csv/tsvregion— domains only:msk(default, Yandex Moscow),gmsk(Google Moscow),spb,rus,nsk,ekb,kzn,nnv,kry,che,sam,ufa,rnd,krr,oms,vrn,prm,vlg,sar,tmn,tom,gkiev,minsk,gminsk,nursulcomparison_type—site_cmponly:intersect(default) /domain1_uniq/domain2_uniqresult_count— return only the total countapi_key— per-call override; otherwiseBUKVARIX_API_KEYenv (defaults tofree)
Query syntax (keywords)
Bukvarix supports operators (percent-encoded automatically):
строител* товары— wildcard!пластиковые !окна— exact match
See query_syntax.html#modifiers.
Free tier limits
numup to 1,000,000; default 250mkeywords:q≤ 100 phrases,q2≤ 250 (101+ ignored)site_mcmp: ≤ 10 domains- Filters
broad_from/to,exact_from/to,length_from/to,words_from/to— paid only (402 on free) - 429 = rate limit, pause and retry. Alternatively download full bases from /about_bases.html.
Installation
git clone https://github.com/frankydzoro/bukvarix-mcp.git
cd bukvarix-mcp
npm install
Usage with Hermes
Add to ~/.hermes/config.yaml:
mcp_servers:
bukvarix:
command: node
args: [/absolute/path/to/bukvarix-mcp/src/index.js]
enabled: true
env:
BUKVARIX_API_KEY: free # or your paid key
Verify:
hermes mcp test bukvarix
Generic MCP config (e.g. Claude Desktop):
{
"mcpServers": {
"bukvarix": {
"command": "node",
"args": ["/absolute/path/to/bukvarix-mcp/src/index.js"],
"env": { "BUKVARIX_API_KEY": "free" }
}
}
}
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.