finnish-foreign-trade-mcp
https://github.com/NectiaAutomation/finnish-trade-mcp-server
README
Finnish Foreign Trade (Tulli) MCP
Query Finland's import and export statistics with your AI agent. Trade by commodity, country, and period — from Finnish Customs (Tulli), delivered as clean, ready-to-read rows. Ask a question in natural language; the server finds the right trade table, figures out its dimensions, and returns the numbers.
Example: "How much did Finland import in total each month last year?" → the agent searches Tulli's trade tables and returns the monthly totals in EUR.
This package is a lightweight, open bridge that connects any MCP client (Claude Desktop, etc.) to the hosted, maintained Finnish Foreign Trade MCP server on Apify. The bridge holds no data logic — it forwards your requests to the hosted service, which does the real work (trade queries + json-stat decoding) and meters usage to your own Apify account.
Tools
| Tool | What it does |
|---|---|
search_trade_tables |
List Tulli trade tables (CN goods, SITC, NACE industry, BEC). |
get_trade_dimensions |
A table's dimensions + classification value codes. |
get_trade_data |
Flattened import/export rows by commodity, country and period. |
Setup
1. Get access + an Apify API token
This bridge calls a hosted, paid Actor on Apify. You need your own Apify account and API token:
- Open the Actor on the Apify Store: https://apify.com/nectia/finnish-foreign-trade-mcp
- Subscribe / rent the Actor (billed per call — pay only for what you use).
- Copy your token from Apify Console → Settings → Integrations → API token.
2. Add it to your MCP client
Claude Desktop (claude_desktop_config.json):
{
"mcpServers": {
"tulli": {
"command": "npx",
"args": ["-y", "finnish-trade-mcp-server"],
"env": {
"APIFY_API_TOKEN": "PASTE_YOUR_APIFY_TOKEN_HERE"
}
}
}
}
Restart your client. No build step, no other keys.
How it works
Your MCP client ──stdio──► finnish-trade-mcp-server (this bridge) ──HTTPS──► Hosted Actor on Apify ──► Tulli/Uljas API
The bridge authenticates to the hosted Actor with your APIFY_API_TOKEN and transparently
proxies the tools. Your token stays on your machine; Apify meters the calls to your account.
Data & attribution
Data © Finnish Customs, Uljas statistical database, licensed CC BY 4.0. This project is not affiliated with or endorsed by Finnish Customs.
License
MIT © Nectia Automation. The bridge code is open source; the hosted Actor is a commercial service.
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.