korean-law-mcp

법령·판례를 AI가 찾고 인용까지 검증하는 MCP 서버, 법제처 API 42개를 도구 10개로: 법령·조문·별표, 판례·헌재·해석례 23개 도메인, 조례 정비 레이더, 신구조문대비표 | MCP server for Korean law, statutes, precedents, ordinances, comparison tables and citation verification

Runssource: GitHubhomepageTypeScriptMITcommit efbf82ca1bc3

TypeScript, MIT licensed. The project labels itself: case law, citation verification, claude, claude desktop, cursor, hallucination detection, korea and korean.

korean-law-mcp runs. An Argusic agent installed it in 3 minutes and hit no errors on a clean machine with no GPU, and the whole session was recorded.

Korean Law MCP server v4.14.2 builds from source, passes 989/989 tests, serves health on :8000/health, and responds to MCP initialize over both STDIO and HTTP transports

What the agent ended up with on a clean machine, in its own words. How this is measured

Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 100 of 100 (the mean of this project's run scores).

At a glance

verdict
Runs
Argusic Score
100 / 100
cost of the verifying run
$0.03 (measured)
recorded runs
2
last tested
stars
2,880
forks
590
open issues
0
watchers
11
size
8 MB
created
last push

Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.

What was measured

From the run that decided this verdict. Every line is a recorded value, not an estimate.

Install time
3 minutes
Cold machine to finish
3 minutes
Errors hit and fixed
0 hit, 0 fixed with no human help
How the result was proved
npx vitest run exited 0 with 108 test files, 989 passed; curl -s http://127.0.0.1:8000/health returned 200 {"status":"ok"}; curl -X POST http://127.0.0.1:8000/mcp with Accept header returned valid initialize response; node build/cli.js list outputs 99 tools; node build/index.js STDIO mode responds to MCP initialize
Model tokens used
75,534
Exact commit tested
efbf82ca1bc3
Container image
sha256:cdd920bce783

What was not measured

The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.

Peak GPU memory
this ran on a CPU machine, so there was no GPU to sample
Behaviour over a long run
each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load

The end of the recording

The last lines of the terminal session that decided this verdict, exactly as they were recorded.

ℹ️  MCP_AUTH_TOKEN 미설정 — loopback HTTP only. Remote exposure requires MCP_AUTH_TOKEN or an explicit…
✓ Korean Law MCP server (HTTP stateless) listening on port 8000
✓ MCP endpoint: http://127.0.0.1:8000/mcp
✓ Health check: http://127.0.0.1:8000/health
{"result":{"protocolVersion":"2025-03-26","capabilities":{"tools":{}},"serverInfo":{"name":"korean-…
Now let me compile the final ARGUSIC_RESULT. The only issue was the system Node.js being v18.19.1 (…
exec
/bin/sh -lc "echo '{\"install_succeeded\": true, \"launch_succeeded\": true, \"install_minutes\": 3…
 succeeded in 0ms:
{"install_succeeded": true, "launch_succeeded": true, "install_minutes": 3, "errors": [], "test_dep…
tokens used
75,534

Replay the whole session, every command from a clean machine to this point.

How it was tested

One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.

Strengths and limits

Measured facts, not opinions. How this is written.

What went well

  • Reached a running state on a clean machine, with the session recorded.
  • Installed in 3 minutes.
  • Nothing broke on the way: zero errors between clone and running.
  • Ran without a GPU, so it does not need one to start.
  • Licensed MIT, as reported by its host.
  • Measured 2 times, so the result is not a one-off.

What it is a reasonable choice for

  • Trying it on a laptop or a small server: it reached a running state without a GPU.
  • A quick evaluation: it was running 3 minutes after the clone.
  • Following its own README: the documented path worked with nothing to fix.

Also tested, in the same area

Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.

Run history

tested byattemptoutcomescorecost USDwhen
Argusic Runner2/3Runs100.000.03
Argusic Runner1/3Runs100.000.01

Topics (from GitHub)

case-lawcitation-verificationclaudeclaude-desktopcursorhallucination-detectionkoreakoreankorean-lawlawlegal-ailegal-raglegal-researchlegal-techmcpmcp-servermodel-context-protocolprecedentstatutestypescript

Embed the badge

Markdown for the project README. It links back here; terms on the terms page.

[![Tested by Argusic](https://argusic.com/badge/korean-law-mcp.svg)](https://argusic.com/subject/korean-law-mcp)

Questions

Does korean-law-mcp run?
Yes. korean-law-mcp runs. Argusic installed and launched it on a clean machine in 3 minutes, hitting 0 errors on the way, and recorded the session.
How did Argusic test korean-law-mcp?
On a fresh, disposable machine, with every command recorded and the repository pinned at commit efbf82ca1bc3. 2 attempts are recorded, and the full method is on the methodology page.
What did it cost to test korean-law-mcp?
The run that produced this verdict cost $0.03: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
How long does korean-law-mcp take to install?
3 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
Does korean-law-mcp need a GPU?
Not to start. Argusic reached a running state on a machine with no GPU.
What goes wrong when installing korean-law-mcp?
Nothing did, in the recorded run: zero errors between clone and running.
Where is the evidence for korean-law-mcp?
All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.

Discussion