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
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.