How do I get a KOSIS API key?

Register at kosis.kr, then apply for API access in the Open API section. Your API key is issued instantly upon application.

What makes Korean data unique?

South Korea is the world's leading producer of memory semiconductors and a major hub for display panels, batteries, and shipbuilding. KOSIS provides granular production, export, and trade data for these critical industries that is unavailable from any other source.

Does the API provide historically consistent data?

Yes, KOSIS standardizes time-series data ensuring that demographic, industrial, and national accounts figures remain historically consistent, often providing data points spanning several decades.

South Korea KOSIS MCP Server for LlamaIndex 2 tools — connect in under 2 minutes

Name: South Korea KOSIS
Availability: InStock
Author: Vinkius

docs.llamaindex.ai/en/stable/module_guides/tools/mcp

Built by Vinkius GDPR 2 Tools Framework

LlamaIndex specializes in data-aware AI agents that connect LLMs to structured and unstructured sources. Add South Korea KOSIS as an MCP tool provider through Vinkius and your agents can query, analyze, and act on live data alongside your existing indexes.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    mcp_client = BasicMCPClient("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    agent = FunctionAgent(
        tools=tools,
        llm=OpenAI(model="gpt-4o"),
        system_prompt=(
            "You are an assistant with access to South Korea KOSIS. "
            "You have 2 tools available."
        ),
    )

    response = await agent.run(
        "What tools are available in South Korea KOSIS?"
    )
    print(response)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About South Korea KOSIS MCP Server

The South Korea KOSIS MCP Server connects your AI agent to the Korean Statistical Information Service — the official data portal for the world's 12th-largest economy and a global powerhouse in semiconductors, automotive, and electronics.

LlamaIndex agents combine South Korea KOSIS tool responses with indexed documents for comprehensive, grounded answers. Connect 2 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.

Core Capabilities

Table Search — Discover statistical tables across all Korean government agencies by keyword. Covers the full spectrum from demographics and national accounts to semiconductor production and trade flows.
Data Retrieval — Pull raw numerical data from any KOSIS table, organized by classification and time period with full unit annotations.
Period Filtering — Narrow results to specific time ranges using start/end period parameters.

Free API key required (instant registration at kosis.kr). South Korea publishes highly granular data covering semiconductor exports, technology adoption, and manufacturing output — intelligence that is critical for supply chain analysis and technology market research.

The South Korea KOSIS MCP Server exposes 2 tools through the Vinkius. Connect it to LlamaIndex in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect South Korea KOSIS to LlamaIndex via MCP

Follow these steps to integrate the South Korea KOSIS MCP Server with LlamaIndex.

Install dependencies

Run pip install llama-index-tools-mcp llama-index-llms-openai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 2 tools from South Korea KOSIS

Why Use LlamaIndex with the South Korea KOSIS MCP Server

LlamaIndex provides unique advantages when paired with South Korea KOSIS through the Model Context Protocol.

Data-first architecture: LlamaIndex agents combine South Korea KOSIS tool responses with indexed documents for comprehensive, grounded answers

Query pipeline framework lets you chain South Korea KOSIS tool calls with transformations, filters, and re-rankers in a typed pipeline

Multi-source reasoning: agents can query South Korea KOSIS, a vector store, and a SQL database in a single turn and synthesize results

Observability integrations show exactly what South Korea KOSIS tools were called, what data was returned, and how it influenced the final answer

South Korea KOSIS + LlamaIndex Use Cases

Practical scenarios where LlamaIndex combined with the South Korea KOSIS MCP Server delivers measurable value.

Hybrid search: combine South Korea KOSIS real-time data with embedded document indexes for answers that are both current and comprehensive

Data enrichment: query South Korea KOSIS to augment indexed data with live information before generating user-facing responses

Knowledge base agents: build agents that maintain and update knowledge bases by periodically querying South Korea KOSIS for fresh data

Analytical workflows: chain South Korea KOSIS queries with LlamaIndex's data connectors to build multi-source analytical reports

South Korea KOSIS MCP Tools for LlamaIndex (2)

These 2 tools become available when you connect South Korea KOSIS to LlamaIndex via MCP:

get_korea_stats_data

Requires orgId and tableId from search_korea_statistics. Optionally filter by time period (YYYYMM or YYYY format). Retrieve statistical data from a specific KOSIS table in South Korea

search_korea_statistics

Returns table IDs, organization IDs, and table names. Use returned orgId and tableId with get_korea_stats_data to retrieve numbers. Common topics: population, GDP, semiconductor exports, technology, employment, trade, education, housing. Search for statistical tables in the South Korean KOSIS national database

Example Prompts for South Korea KOSIS in LlamaIndex

Ready-to-use prompts you can give your LlamaIndex agent to start working with South Korea KOSIS immediately.

"What are South Korea's semiconductor export figures for the last 3 years?"

"What is South Korea's current population growth rate?"

"Show me the employment statistics for the manufacturing sector this quarter."

Troubleshooting South Korea KOSIS MCP Server with LlamaIndex

Common issues when connecting South Korea KOSIS to LlamaIndex through the Vinkius, and how to resolve them.

BasicMCPClient not found

Install: pip install llama-index-tools-mcp

South Korea KOSIS + LlamaIndex FAQ

Common questions about integrating South Korea KOSIS MCP Server with LlamaIndex.

How does LlamaIndex connect to MCP servers?

Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.

Can I combine MCP tools with vector stores?

Yes. LlamaIndex agents can query South Korea KOSIS tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.