bizmachine-mcp
Access Czech and Slovak company data (financials, contacts, risks, ownership) via BizMachine API, enabling natural-language lookups by name, domain, or ICO.
README
bizmachine-mcp
MCP server for BizMachine — Czech and Slovak company data API. Look up revenue, employees, financials, contacts, risk signals, engagement scores, ownership, NACE classification and more for any Czech or Slovak company by name, domain, or ICO.
Tools
Search & core
| Tool | Description |
|---|---|
suggest |
Search companies by name or domain → ICO |
company |
Get full raw aggregated data by ICO |
lookup |
Smart lookup: name/domain → best match → structured data with revenue |
bulk_lookup |
Batch lookup for multiple companies |
Company profile & areas
Every tool below accepts either an ico or a query (name/domain, auto-resolved CZ→SK):
| Tool | Description |
|---|---|
profile |
Rich connector-style profile: identity, address, classification, size, financials, scores, contacts, risk, signal counts — in one call |
contacts |
Phone, email, website, LinkedIn, Facebook, Twitter |
financials |
Revenue, growth, EBIT, EBITDA, margins, assets, registered capital, personnel cost, exporter/importer |
risks |
Risk signals (insolvency, liquidation, executions, tax arrears) + health status |
metrics |
All available BizMachine metrics, normalized |
indicators |
Engagement scores (activity, growth, reachability) with top weighted drivers |
nace |
NACE industry classification (primary + secondary) |
owned_companies |
Subsidiaries / held stakes (downward ownership graph) |
Setup
1. Get API Key
Sign up at bizmachine.com and get your API key.
2. Install
git clone https://github.com/davidsimoes/bizmachine-mcp.git
cd bizmachine-mcp
npm install
3. Configure Claude Code
Add to your ~/.claude/settings.local.json:
{
"mcpServers": {
"bizmachine": {
"command": "node",
"args": ["/path/to/bizmachine-mcp/index.mjs"],
"env": {
"BIZMACHINE_API_KEY": "your_key"
}
}
}
}
Usage
Once registered, Claude gets these tools automatically:
# Quick lookup by domain or name
mcp__bizmachine__lookup("mixit.cz")
mcp__bizmachine__lookup("Košík")
# Batch lookup
mcp__bizmachine__bulk_lookup(["alza.cz", "rohlik.cz", "mixit.cz"])
# Rich, connector-style profile (by name/domain or ICO)
mcp__bizmachine__profile({ query: "alza.cz" })
mcp__bizmachine__profile({ ico: "27082440" })
# Focused areas (each accepts ico OR query)
mcp__bizmachine__contacts({ query: "alza.cz" }) # incl. LinkedIn
mcp__bizmachine__financials({ ico: "27082440" })
mcp__bizmachine__risks({ query: "Sberbank" }) # liquidation, insolvency…
mcp__bizmachine__indicators({ query: "rohlik.cz" }) # engagement scores
mcp__bizmachine__nace({ ico: "24836451" })
mcp__bizmachine__owned_companies({ ico: "27082440" })
mcp__bizmachine__metrics({ query: "mixit.cz" })
# Raw search / full data
mcp__bizmachine__suggest("alza")
mcp__bizmachine__company("27082440")
Features
- Smart domain matching: When given a domain, queries the API and matches results by website URL, then falls back to name matching
- One composite call:
profileand the area tools all read BizMachine'saggregated-dataendpoint, so a single fetch (cached) powers identity, financials, contacts, risk, scores and classification - Revenue extraction: Handles both exact values and range estimates (midpoint)
- Name normalization: Strips Czech legal suffixes (s.r.o., a.s., etc.) and diacritics for fuzzy matching
- CZ + SK with auto-fallback: Query tools try the Czech database first, then Slovak
- 30-day file cache: Results cached in
~/.cache/bizmachine/to avoid redundant API calls - Rate limiting: 150ms between API calls
API plan tiers
The data each tool can return depends on your BizMachine API plan. The tools above are built on the endpoints available to a standard data key (suggest, aggregated-data, indicators, owned-companies). Some BizMachine datasets — detailed financial statements (line items), individual vehicle/fleet records, public-tender and job-posting listings, subsidies, and individual-person contacts — require a higher plan tier and are exposed by BizMachine as separate endpoints. Where only summary/count-level data is available on the standard tier (e.g. fleet size, open-job count, e-shop count), it is surfaced via metrics and profile.signals.
Development
Pure data-shaping logic lives in lib/extract.mjs (no I/O), the API client in
lib/api.mjs, and MCP wiring in index.mjs. Run the unit tests (no API key
needed — they exercise the pure helpers):
npm test
License
MIT
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。