Skip to main content
Glama
LexLink

LexLink

by rabqatab

Read this in other languages: English | 한국어 (Korean)

Kakao PlayMCP 10 3rd Prize MCP Python

LexLink is an MCP (Model Context Protocol) server that wraps the Korean National Law Information API (open.law.go.kr) so AI agents can search and read Korean laws, case law, interpretations and related material.

What it provides

  • 68 tools, 9 prompts and 2 resources (v2.2.0, plus the Unreleased changes listed in CHANGELOG.md).

  • Laws by effective date or announcement date, single articles (jo), English translations, administrative rules, local ordinances, treaties.

  • Court precedents, Constitutional Court decisions, legal interpretations, administrative appeals, committee decisions, ministry interpretations, special tribunals.

  • law_as_of: the version of a law (or one article) in force on a given date.

  • article_citation: citations referenced by one article, extracted from law.go.kr HTML (no LLM). Edge cases (ranges, deleted articles) are listed under limitations in the API reference.

  • AI/semantic search (aiSearch, aiRltLs_search) and one-call chain tools (chain_*).

  • Per-tool TTL cache and Korean law-name abbreviation resolution (e.g. 자통법).

  • JSON by default; type="XML" or "HTML" on request.

  • Errors come back as {status: "error", error_code, message, hints, request_id}.

All tool names and arguments are in the API reference.

Related MCP server: Korean Law MCP Server

Tool groups

Group

Tools

Laws

eflaw_search, law_search, eflaw_service, law_service, eflaw_josub, law_josub, law_as_of, elaw_search, elaw_service

Admin rules, ordinances, linkage

admrul_*, ordin_*, ordinLsCon_search, lnkLs_search, lnkLsOrdJo_search, lnkDep_search, drlaw_search, lsDelegated_service

Case law and decisions

prec_*, detc_*, expc_*, decc_*, committee_*, cgm_expc_*, special_decc_*

Treaties

trty_search, trty_service

AI search and knowledge base

aiSearch, aiRltLs_search, lstrm_ai_search, dlytrm_search, lstrm_rlt_search, dlytrm_rlt_search, lstrm_rlt_jo_search, jo_rlt_lstrm_search, ls_rlt_search

History, comparison, appendix, dictionary

oldAndNew_*, thdCmp_*, lsJoHstInf_search, lsHstInf_search, delHst_search, lsAbrv_search, licbyl_search, lstrm_*

Analysis

article_citation, check_precedent_odds, legal_resolver, simplify_article, law_amendment_summary, article_amendment_diff

Chains and ops

chain_full_research, chain_amendment_track, chain_dispute_prep, chain_law_system, cache_stats

Which tool to start with:

You have

Start with

A vague question in plain Korean

legal_resolver, aiSearch, aiRltLs_search

A law name and article number

eflaw_search (get MST) then eflaw_josub / eflaw_service with jo

"What did the law say on date D?"

law_as_of

Old/new article text of an amendment

oldAndNew_search then oldAndNew_service

Law, 시행령 and 시행규칙 side by side

thdCmp_search then thdCmp_service with jo (very large without it)

What a legal term means

lstrm_search then lstrm_service (dictionary); lstrm_ai_search only gives related-term links

A topic for case law

prec_search, detc_search, chain_dispute_prep

For article text always pass jo (e.g. 35, "35의5", "제35조의5", "003505"; normalized to 6 digits). Without it some laws return a very large body.

Prompts: search-korean-law, get-law-article, get-article-with-citations, analyze-law-citations, search-admin-rules, tool-selection-guide, analyze-legal-situation, explain-legal-document, check-legal-precedent.

Resources: lexlink://laws/frequently-used (about 20 common law names mapped to 법령ID) and the template lexlink://law/{name} (read it as e.g. lexlink://law/자통법, without braces; the name is URL-decoded, resolver aliases are applied, and one live law_search exact-name lookup is the fallback).

Quick start

Requires Python 3.10+ and uv. You also need an OC from open.law.go.kr: the part of your registered email before the @. law.go.kr checks the OC together with the caller's IP, so the machine running LexLink may need its IP registered there.

uv sync

# stdio (Claude Code, Cursor, other local MCP clients)
OC=<OC> uv run stdio

# Streamable HTTP at /mcp (HTTP mode refuses to start without auth settings)
OC=<OC> LEXLINK_AUTH_TOKENS=local:<TOKEN> TRANSPORT=http uv run serve

The server does not read .env by itself. Export the variables, or run uv run --env-file .env stdio.

OC is resolved as: tool argument oc first, then the OC environment variable. In HTTP mode the oc argument is ignored and the server's OC is always used.

For HTTP deployment (auth, TLS proxy, rate limits, logging) see docs/OPERATIONS.md.

Environment variables

Variable

Default

Description

OC

(required)

law.go.kr API identifier

LEXLINK_BASE_URL

http://www.law.go.kr

Upstream base URL

LEXLINK_TIMEOUT

60

Upstream request timeout (seconds)

SLIM_RESPONSE

unset

1/true/yes/on turns on the compact mode for size-limited hosts such as PlayMCP: drops raw_content when ranked_data exists, keeps the compact caps (500-char excerpts, top-10/3 lists, 80 delegation entries) and trims any result over 20,000 bytes (truncated, truncated_notes). Unset: nothing already fetched is cut (one exception: simplify_article looks up at most 20 legal terms)

TRANSPORT

sse

HTTP server only: http (recommended) or sse

The HTTP-only variables (HOST, PORT, LEXLINK_AUTH_TOKENS, rate limits, logging, ...) are in docs/OPERATIONS.md.

Example

eflaw_search(query="자동차관리법", display=5)
# {"status": "ok", "request_id": "...", "upstream_type": "JSON", "ranked_data": ..., "raw_content": ...}

eflaw_josub(mst="<MST from the search>", jo="제3조")

Error codes: VALIDATION_ERROR, TIMEOUT, UPSTREAM_ERROR, INTERNAL_ERROR, NOT_FOUND, ARTICLE_NOT_FOUND, EMPTY_RESPONSE, API_NOT_SUBSCRIBED, UPSTREAM_HTML_ERROR. See the API reference.

Documentation

Doc

For

docs/README.md

Index

docs/API_REFERENCE.md

Tool list, arguments, upstream API catalog, limitations

docs/OPERATIONS.md

HTTP server: deploy, auth, TLS proxy, logging (Korean)

docs/DEVELOPMENT.md

Code layout, tests, adding tools

CHANGELOG.md

Release history, Unreleased changes

AGENTS.md

Notes for coding agents

Contributing

Fork, branch, add tests, run uv run pytest tests/, open a pull request. Details in docs/DEVELOPMENT.md.

License

No LICENSE file is included in this repository.

Acknowledgments

  • law.go.kr - Korean National Law Information API

  • MCP - Model Context Protocol by Anthropic

  • korean-law-mcp - inspiration for caching, law name resolution and chain tools

Support

Available Tools

26 tools
admrul_serviceA
Read-onlyIdempotent

Retrieve administrative rule full text (행정규칙 본문 조회).

This tool retrieves the complete text of Korean administrative rules. Includes rule content, addenda, and annexes (forms/attachments).

Args: id: Rule sequence number (required if lid/lm not provided) lid: Rule ID (alternative to id) lm: Rule name (exact match search) oc: Optional OC override (defaults to env var) type: Response format - "HTML" or "XML" (default "XML", JSON not supported by API) ctx: MCP context (injected automatically)

Returns: Full administrative rule text with content and annexes or error

Examples: Retrieve by ID: >>> admrul_service(id="62505", type="XML")

Retrieve by LID:
>>> admrul_service(lid="10000005747", type="XML")

Inputs: id, lid, lm, oc, +1 more.

aiSearchA
Read-onlyIdempotent

⭐ PREFERRED TOOL for vague or natural language queries. Use this FIRST when user's intent is unclear or conversational.

지능형 법령검색 시스템 검색 API (AI-powered semantic law search).

Uses intelligent/semantic search to find relevant law articles. Returns FULL ARTICLE TEXT (조문내용) - more comprehensive than eflaw_search.

Best for: Natural language queries like "뺑소니 처벌", "음주운전 벌금"

Args: query: Search query (natural language supported, e.g., "뺑소니 처벌") search: Search scope: - 0: 법령조문 (law articles, default) - 1: 법령 별표·서식 (law appendix/forms) - 2: 행정규칙 조문 (administrative rule articles) - 3: 행정규칙 별표·서식 (administrative rule appendix/forms) display: Results per page (default 20) page: Page number (default 1) oc: Optional OC override type: Response format - XML only (JSON not supported)

Returns: AI search results with full article text (법령조문 items with 조문내용)

Example: >>> aiSearch(query="뺑소니 처벌", search=0) # Returns: 특정범죄 가중처벌 등에 관한 법률 제5조의3 (도주차량 운전자의 가중처벌)

Inputs: query (required), search, display, page, +2 more.

article_citationA
Read-onlyIdempotent

Extract citations from a law article (조문 인용 조회).

This tool extracts all legal citations referenced by a specific law article. It parses the official hyperlinked citations from law.go.kr HTML pages, providing 100% accurate citation data with zero API cost.

The tool identifies:

  • External citations (references to other laws)

  • Internal citations (references within the same law)

  • Article, paragraph, and item level references

Args: mst: Law MST code (법령일련번호) - get this from eflaw_search or law_search results law_name: Law name in Korean (e.g., "자본시장과 금융투자업에 관한 법률") article: Article number (조번호, e.g., 3 for 제3조) article_branch: Article branch number (조가지번호, e.g., 2 for 제37조의2, default 0) oc: Optional OC override (defaults to env var)

Returns: Citation extraction result with: - success: Whether extraction succeeded - law_id: MST code - law_name: Law name - article: Article display (e.g., "제3조" or "제37조의2") - citation_count: Total number of citations found - citations: List of citation objects with target law, article, paragraph, item - internal_count: Number of same-law citations - external_count: Number of other-law citations

Examples: Get citations from 자본시장법 제3조: >>> article_citation( ... mst="268611", ... law_name="자본시장과 금융투자업에 관한 법률", ... article=3 ... )

Get citations from 건축법 제37조의2:
>>> article_citation(
...     mst="270986",
...     law_name="건축법",
...     article=37,
...     article_branch=2
... )

Workflow: 1. First use eflaw_search(query="법명") to find the law and get MST 2. Then use article_citation(mst=..., law_name=..., article=...) to get citations 3. Optionally use eflaw_service to get the full article text

Inputs: mst (required), law_name (required), article (required), article_branch, +1 more.

decc_serviceA
Read-onlyIdempotent

Retrieve administrative appeal decision full text (행정심판례 본문 조회).

This tool retrieves the complete text of Korean administrative appeal decisions. Includes case details, disposition information, decision summary, and reasoning.

Args: id: Decision sequence number (required) lm: Decision name (optional) oc: Optional OC override (defaults to env var) type: Response format - "HTML" or "XML" (default "XML", JSON not supported by API) ctx: MCP context (injected automatically)

Returns: Full administrative appeal decision text with details or error

Examples: Retrieve by ID: >>> decc_service(id="243263", type="XML")

Retrieve with case name:
>>> decc_service(id="245011", lm="과징금 부과처분 취소청구", type="XML")

Inputs: id (required), lm, oc, type.

detc_serviceA
Read-onlyIdempotent

Retrieve Constitutional Court decision full text (헌재결정례 본문 조회).

Args: id: Constitutional Court decision sequence number (헌재결정례일련번호) lm: Decision name (optional) oc: Optional OC override type: Response format - "HTML" or "XML" (default "XML")

Returns: Full Constitutional Court decision text or error

Examples: >>> detc_service(id="58386")

Inputs: id (required), lm, oc, type.

eflaw_josubA
Read-onlyIdempotent

Query specific article/paragraph by effective date (시행일 기준 조·항·호·목 조회).

BEST TOOL for querying specific articles like "제174조", "제3조" etc. This returns only the requested article/paragraph, avoiding large full-law responses.

Args: id: Law ID (either id or mst is required) mst: Law serial number (MST) ef_yd: Effective date (YYYYMMDD) - required when using mst jo: Article number in XXXXXX format. Format: first 4 digits = article number (zero-padded), last 2 digits = branch suffix (00=main). Examples: "017400" (제174조), "017200" (제172조), "000300" (제3조), "001502" (제15조의2) hang: Paragraph number (6 digits, e.g., "000100" for 제1항) ho: Item number (6 digits, e.g., "000200" for 제2호) mok: Subitem (UTF-8 encoded, e.g., "다" for 다목) oc: Optional OC override (defaults to env var) type: Response format - "HTML" or "XML" (default "XML", JSON not supported by API)

Returns: Specific law section content

Examples: Query 자본시장법 제174조: >>> eflaw_josub(mst="279823", jo="017400", type="XML")

Query 건축법 제3조 제1항:
>>> eflaw_josub(mst="276925", jo="000300", hang="000100", type="XML")

Inputs: id, mst, ef_yd, jo, +5 more.

eflaw_serviceA
Read-onlyIdempotent

Retrieve full law content by effective date (시행일 기준 법령 본문 조회).

Retrieves the complete text of a law organized by effective date.

IMPORTANT: For specific article queries (e.g., "제174조"), ALWAYS use the jo parameter. Some laws (e.g., 자본시장법) have 400+ articles and the full response can exceed 1MB. Using jo returns only the requested article, which is much faster and cleaner.

Args: id: Law ID (either id or mst is required) mst: Law serial number (MST/lsi_seq) ef_yd: Effective date (YYYYMMDD) - required when using mst jo: REQUIRED for specific articles. Article number in XXXXXX format. Format: first 4 digits = article number (zero-padded), last 2 digits = branch suffix (00=main). Examples: "017400" (제174조), "017200" (제172조), "000300" (제3조), "001502" (제15조의2) chr_cls_cd: Language code - "010202" (Korean, default) or "010201" (Original) oc: Optional OC override (defaults to env var) type: Response format - "HTML" or "XML" (default "XML", JSON not supported by API)

Returns: Full law content or specific article content

Examples: Retrieve specific article (RECOMMENDED): >>> eflaw_service(mst="279823", jo="017400", type="XML") # 자본시장법 제174조

Retrieve full law (WARNING: large response for some laws):
>>> eflaw_service(id="1747", type="XML")

Inputs: id, mst, ef_yd, jo, +3 more.

elaw_serviceA
Read-onlyIdempotent

Retrieve English law full text (영문법령 본문 조회).

This tool retrieves the complete text of Korean laws translated to English. Useful for international legal research and cross-border understanding.

Args: id: Law ID (required if mst not provided) mst: Law master number (required if id not provided) lm: Law name (alternative search method) ld: Announcement date (YYYYMMDD) ln: Announcement number oc: Optional OC override (defaults to env var) type: Response format - "HTML" or "XML" (default "XML", JSON not supported by API) ctx: MCP context (injected automatically)

Returns: Full English law text with articles or error

Examples: Retrieve by ID: >>> elaw_service(id="000744", type="XML")

Retrieve by MST:
>>> elaw_service(mst="127280", type="XML")

Inputs: id, mst, lm, ld, +3 more.

expc_serviceA
Read-onlyIdempotent

Retrieve legal interpretation full text (법령해석례 본문 조회).

This tool retrieves the complete text of a legal interpretation precedent, including the question summary, answer, and reasoning.

Args: id: Legal interpretation sequence number (required) lm: Legal interpretation name (optional) oc: Optional OC override (defaults to env var) type: Response format - "HTML" or "XML" (default "XML", JSON not supported by API) ctx: MCP context (injected automatically)

Returns: Full legal interpretation text with question, answer, and reasoning or error

Examples: Retrieve by ID: >>> expc_service(id="334617", type="XML")

Retrieve with name:
>>> expc_service(id="315191", lm="여성가족부 - 건강가정기본법 제35조 제2항 관련", type="XML")

Inputs: id (required), lm, oc, type.

law_josubA
Read-onlyIdempotent

Query specific article/paragraph by announcement date (공포일 기준 조·항·호·목 조회).

BEST TOOL for querying specific articles like "제174조", "제3조" etc. This returns only the requested article/paragraph, avoiding large full-law responses.

Args: id: Law ID (either id or mst is required) mst: Law serial number (MST) jo: Article number in XXXXXX format. Format: first 4 digits = article number (zero-padded), last 2 digits = branch suffix (00=main). Examples: "017400" (제174조), "017200" (제172조), "000300" (제3조), "001502" (제15조의2) hang: Paragraph number (6 digits, e.g., "000100" for 제1항) ho: Item number (6 digits, e.g., "000200" for 제2호) mok: Subitem (UTF-8 encoded, e.g., "다" for 다목) oc: Optional OC override (defaults to env var) type: Response format - "HTML" or "XML" (default "XML", JSON not supported by API)

Returns: Specific law section content

Examples: Query 자본시장법 제174조: >>> law_josub(mst="279823", jo="017400", type="XML")

Query 건축법 제3조 제1항:
>>> law_josub(mst="276925", jo="000300", hang="000100", type="XML")

Inputs: id, mst, jo, hang, +4 more.

law_serviceA
Read-onlyIdempotent

Retrieve full law content by announcement date (공포일 기준 법령 본문 조회).

Retrieves the complete text of a law organized by announcement (publication) date.

IMPORTANT: For specific article queries (e.g., "제174조"), ALWAYS use the jo parameter. Some laws (e.g., 자본시장법) have 400+ articles and the full response can exceed 1MB. Using jo returns only the requested article, which is much faster and cleaner.

Args: id: Law ID (either id or mst is required) mst: Law serial number (MST) lm: Law modification parameter ld: Law date parameter (YYYYMMDD) ln: Law number parameter jo: REQUIRED for specific articles. Article number in XXXXXX format. Format: first 4 digits = article number (zero-padded), last 2 digits = branch suffix (00=main). Examples: "017400" (제174조), "017200" (제172조), "000300" (제3조), "001502" (제15조의2) lang: Language - "KO" (Korean) or "ORI" (Original) oc: Optional OC override (defaults to env var) type: Response format - "HTML" or "XML" (default "XML", JSON not supported by API)

Returns: Full law content or specific article content

Examples: Retrieve specific article (RECOMMENDED): >>> law_service(mst="279823", jo="017400", type="XML") # 자본시장법 제174조

Retrieve full law (WARNING: large response for some laws):
>>> law_service(id="009682", type="XML")

Inputs: id, mst, lm, ld, +5 more.

lsDelegated_serviceA
Read-onlyIdempotent

Retrieve delegated laws/rules/ordinances (위임 법령 조회).

This tool retrieves information about laws, administrative rules, and local ordinances that are delegated by a parent law. Shows the delegation hierarchy and which specific articles delegate authority.

⚠️ Note: This API does NOT support HTML format (only XML/JSON).

Args: id: Law ID (required if mst not provided) mst: Law master number (required if id not provided) oc: Optional OC override (defaults to env var) type: Response format - "XML" only (JSON not supported by API, HTML not available) ctx: MCP context (injected automatically)

Returns: Delegation hierarchy with delegated laws/rules/ordinances or error

Examples: Retrieve delegations for 초·중등교육법: >>> lsDelegated_service(id="000900", type="XML")

Inputs: id, mst, oc, type.

prec_serviceA
Read-onlyIdempotent

Retrieve court precedent full text (판례 본문 조회).

Args: id: Precedent sequence number (판례일련번호) lm: Precedent name (optional) oc: Optional OC override type: Response format - "HTML" or "XML" (default "XML")

Returns: Full precedent text with details or error

Examples: >>> prec_service(id="228541")

Inputs: id (required), lm, oc, type.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A3.7/5.0

    Scored across 26 tools

    Disambiguation3/5

    The tools are organized into clear categories like laws, administrative rules, precedents, and interpretations, which helps distinguish them. However, there is significant overlap within categories, such as multiple search tools for laws (eflaw_search, law_search, aiSearch, aiRltLs_search) that could confuse agents about which to use first. The descriptions provide guidance (e.g., 'PREFERRED TOOL' notes), but the redundancy creates ambiguity.

    Naming Consistency2/5

    Naming is inconsistent across the toolset. Some tools use snake_case (admrul_search, eflaw_service), others use camelCase (aiRltLs_search, lnkDep_search), and some mix styles (drlaw_search). There is no uniform verb_noun pattern; for example, search tools vary (search vs. service suffixes), and tools like article_citation deviate entirely. This inconsistency makes the set harder to navigate.

    Tool Count2/5

    With 26 tools, the count is excessive for a legal search server, leading to complexity and potential confusion. While the domain (Korean legal research) is broad, many tools are redundant (e.g., eflaw_search and law_search for similar law searches) or highly specialized (e.g., drlaw_search for linkage statistics). A more streamlined set of 10-15 tools could cover the same functionality more coherently.

    Completeness4/5

    The toolset is highly complete for Korean legal research, covering laws, administrative rules, precedents, interpretations, English translations, and linkages. Each category typically includes search and retrieval tools (e.g., search and service pairs), providing good lifecycle coverage. Minor gaps exist, such as no tool for comparing law versions over time, but overall, the surface is comprehensive for the domain.

    Maintenance

    ActivityMaintained
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • -
      license
      Not graded
      quality
      Not graded
      maintenance
      Enables searching and retrieving Korean legal information including laws, court precedents, legal interpretations, and local ordinances from the Korean National Law Information Center API with intelligent search ranking.
      -
    • F
      license
      Not graded
      quality
      D
      maintenance
      Enables real-time search and analysis of Korean laws, legal precedents, and administrative rules through the National Law Information Center Open API, allowing AI agents to access official legal information for contract review, compliance, and legal research.
      74
      -
    • F
      license
      Not graded
      quality
      C
      maintenance
      Enables AI to search and retrieve South Korean legal information from the National Law Information Center. It allows users to look up specific laws, articles, and detailed legal provisions using natural language queries.
      135
      -
    • A
      license
      A
      quality
      D
      maintenance
      Enables users to search and retrieve South Korean statutes, precedents, and administrative rules via the National Law Information Center API. It supports deep legal chain analysis, legislative history tracking, and legal terminology lookups through natural language.
      10
      134 PyPI
      5
      MIT