Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/choiyounggi/korea-data-suiteWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/choiyounggi/korea-data-suite/korea-data-mcp-korea-data-mcp)<a href="https://agentmods.dev/mcp/choiyounggi/korea-data-suite/korea-data-mcp-korea-data-mcp"><img src="https://agentmods.dev/badge/mcp/choiyounggi/korea-data-suite/korea-data-mcp-korea-data-mcp/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/choiyounggi/korea-data-suite/korea-data-mcp-korea-data-mcp"><img src="https://agentmods.dev/badge/mcp/choiyounggi/korea-data-suite/korea-data-mcp-korea-data-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
korea-data-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 12d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
{
"korea-data-mcp": {
"command": "uvx",
"args": [
"korea-data-mcp"
],
"env": {
"KDS_API_KEY": "",
"KDS_API_BASE": ""
}
}
}What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 12d ago First seen · 12 lines scan A b1a3fc66fca0
korea-data-mcp is an MCP server published in the GitHub repository choiyounggi/korea-data-suite (2 stars, last pushed 21d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
aimarket-hub
Search and invoke real AI capabilities on modelmarket.dev. Free trial, then USDC on Base. Remote server at modelmarket.dev.
krx-etf-mcp
MCP server "krx-etf-mcp" as configured in dongkyucho17/krx-etf-mcp. Runs locally from the krx-etf-mcp Python package.
floweringagents-mcp
MCP server giving AI agents tools to self-register and report real economic performance on FloweringAgents. Runs locally from the floweringagents-mcp Python package.
publicdata-kr
MCP server "publicdata-kr" as configured in fieldcure/fieldcure-mcp-publicdata. Launched with FieldCure.Mcp.PublicData.Kr. Needs 3 environment variables to run.
xfinlab
Real-time market events, sentiment, and technical analysis as MCP tools, backed by real data. Remote server at api.xfinlab.com.
fastapi-scaffolder
MCP server "fastapi-scaffolder" as configured in SevenDeadlyCommits/fastapiscaffolder. Runs locally from the fastapi-scaffolder Python package.