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/obundh/korea-public-data-catalog-mcpWrote 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/obundh/korea-public-data-catalog-mcp/korea-public-data-catalog)<a href="https://agentmods.dev/mcp/obundh/korea-public-data-catalog-mcp/korea-public-data-catalog"><img src="https://agentmods.dev/badge/mcp/obundh/korea-public-data-catalog-mcp/korea-public-data-catalog/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/obundh/korea-public-data-catalog-mcp/korea-public-data-catalog"><img src="https://agentmods.dev/badge/mcp/obundh/korea-public-data-catalog-mcp/korea-public-data-catalog.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
korea-public-data-catalog 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-public-data-catalog": {
"type": "stdio",
"command": "node",
"args": [
"${CLAUDE_PROJECT_DIR:-.}/dist/index.js"
],
"env": {
"KOREA_PUBLIC_DATA_MODE": "catalog"
}
}
}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 b47a45a3342a
korea-public-data-catalog is an MCP server published in the GitHub repository obundh/korea-public-data-catalog-mcp (15 stars, last pushed 1mo 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 2026-08-30.
Other mcp servers, from other repositories
academyinfo
Compare 488 Korean universities on 17 official disclosure indicators (대학알리미). No API key. Runs locally from the academyinfo-mcp npm package.
jma-data-mcp
MCP server "jma-data-mcp" as configured in koizumikento/jma-data-mcp. Runs locally from the jma-data-mcp Python package.
mcp-stashbox
Search scenes, performers, studios and tags across the public stash-box catalogues. Runs locally from the mcp-stashbox npm package. Needs 12 environment variables to run.
civicdataforge
Ten government-record evidence tools for property, healthcare, facilities, Norway, and routing. Remote server at civicdataforge.pages.dev.
reevl-mcp
MCP server "reevl-mcp", hosted remotely at reevl.co.kr, as configured in exclusiveyon-a11y/reevl-mcp.
mcportal
Quota-guarded runtime layer bridging Korean public data APIs (data.go.kr) into the MCP ecosystem. Runs locally from the mcportal Python package.