Agent skill

LexGuard MCP Developer Guide

by SeoNaRu in SeoNaRu/lexguard-mcp

Developer guide for the LexGuard Korean law MCP server: layer rules, adding tools and repositories, JSON-RPC responses, law API handling, answer rules and tests.

Custom licenceAuto-check passedAgent Workflows

SKILL.md written in Korean; this summary is our English description.

Install LexGuard MCP Developer Guide

skills CLI
$ npx skills add SeoNaRu/lexguard-mcp --skill lexguard-mcp-dev -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install SeoNaRu/lexguard-mcp lexguard-mcp-dev --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/SeoNaRu/lexguard-mcp.git skills-src && mkdir -p .claude/skills && cp -r skills-src/.cursor/skills/lexguard-mcp-dev .claude/skills/lexguard-mcp-dev && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
lexguard-mcp-dev
GitHub stars
131
Token cost
~1.1k tokens
SKILL.md length
214 words
Files
1
Skills in repo
1
Repo updated
First seen
Licence
Custom licence

At a glance

Developer guide for the LexGuard Korean law MCP server: layer rules, adding tools and repositories, JSON-RPC responses, law API handling, answer rules and tests.

  • Works in 4 steps: tools/list에 툴 스키마 추가 (mcp_routes.py 내… → tools/call에 분기 추가 (tool_name 조건문) → Service 메서드 작성 (기존 SmartSearchService 패턴… → …
  • Adding a new MCP tool to the LexGuard server
  • SKILL.md covers 아키텍처 패턴, 새 MCP 툴 추가 체크리스트, 새 Repository 패턴 and MCP JSON-RPC 응답 형식, plus 5 more sections
  • Calls pytest

What it does

Requests flow from an MCP client to a `POST /mcp` JSON-RPC endpoint in `mcp_routes.py`, then to a service, then to a repository that calls the national law API. Routes handle JSON-RPC parsing, SSE streaming and the tool and prompt listings. Services hold business logic and may combine repositories, and each repository wraps one law API and must inherit `BaseLawRepository`. Adding a tool means adding its schema to the tools list, a branch in the tool-call handler, a service method modeled on `SmartSearchService`, and a README update.

Law API rules require `attach_api_key` for keys, cached searches for 30 minutes and cached failures for five, the four `API_ERROR_*` codes, and a call to `validate_drf_response` on every reply. Tool descriptions must forbid emoji, titles, full article quotations, definitive conclusions and exposed API links, and require hedged wording and requests for more information. The contract review tool combines a common instruction with a labor-contract add-on. Tests run with `pytest tests/ -v`, favoring pure-logic tests that need no API key. The guide is written in Korean.

When your agent uses it

  • Adding a new MCP tool to the LexGuard server
  • Writing a repository that wraps another national law API endpoint
  • Changing the JSON-RPC endpoint or the response formatting
  • Writing tests for services that run without an API key

Example prompts

  • “Add a new MCP tool that looks up administrative rules, following the existing service and repository pattern.”
  • “Write a repository for the precedent search API that inherits BaseLawRepository and uses the caches.”
  • “Add pytest coverage for the contract review instruction without needing a law API key.”

Requirements

  • Python with pytest
  • A key for the Korean national law information API

Workflow steps

4 steps, taken from the first numbered list in SKILL.md.

  1. tools/list에 툴 스키마 추가 (mcp_routes.py 내 tools_list 배열)
  2. tools/call에 분기 추가 (tool_name 조건문)
  3. Service 메서드 작성 (기존 SmartSearchService 패턴 참고)
  4. README.md 업데이트

What it can do on your machine

Read from SKILL.md and the folder at commit 6f7da76. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Shell commands in SKILL.md call:

    • pytest

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    No URLs in SKILL.md.

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names no API keys, tokens, secrets or passwords.

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

LexGuard MCP Developer Guide loads about 1.1k tokens when it runs. Until then it costs about 45 tokens; SKILL.md has 214 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~45
When it runs · the whole SKILL.md, loaded when a task matches
~1.1k

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); files beside SKILL.md are not scanned.

SKILL.md

Its licence (Custom licence) doesn't allow us to republish the file, so here is its outline and opening line. It has 214 words (~1,080 tokens).

name
lexguard-mcp-dev

Read the full SKILL.md on GitHub

Files

Just SKILL.md in .cursor/skills/lexguard-mcp-dev of SeoNaRu/lexguard-mcp.

Open the folder on GitHubat commit 6f7da76

Compare with similar skills

LexGuard MCP Developer Guide next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

LexGuard MCP Developer Guide compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
LexGuard MCP Developer Guide this skillSeoNaRu/lexguard-mcp131—~1.1kAutomated safety check: PassCustom licence
MCP Server Builderanthropics/skills180k63 repos~2.3kAutomated safety check: PassApache-2.0
MCP Server BuildershareAI-lab/learn-claude-code78k5 repos~1.2kAutomated safety check: PassMIT
Python TestsPrefectHQ/fastmcp28k—~466Automated safety check: PassApache-2.0
Tiger Brokers OpenAPI SDKqusong0627/QuantMind1.7k—~1.4kAutomated safety check: PassApache-2.0
Opik Online Evalcomet-ml/opik-mcp220—~3kAutomated safety check: NotesApache-2.0

Similar skills

  • MCP Server Builder

    anthropics/skills

    Official

    Guides the design and implementation of Model Context Protocol servers in TypeScript or Python, from tool naming and error messages to evaluation.

    180k GitHub starsUsed in 63 repos~2.3k tokens
    Agent WorkflowsAuto-check passed
  • MCP Server Builder

    shareAI-lab/learn-claude-code

    Walks through building MCP servers in Python or TypeScript that expose tools, resources and prompts to Claude, with templates, registration and testing.

    78k GitHub starsUsed in 5 repos~1.2k tokens
    Agent WorkflowsAuto-check passed
  • Python Tests

    PrefectHQ/fastmcp

    Write regression tests for FastMCP changes using its pytest fixtures, in-memory clients, and protocol boundaries.

    28k GitHub stars~466 tokensUpdated today
    Agent WorkflowsAuto-check passed
  • Tiger Brokers OpenAPI SDK

    qusong0627/QuantMind

    Covers the Tiger Brokers OpenAPI Python SDK for market data, stock, futures and options trading, push subscriptions, a CLI and an MCP server, defaulting to paper trading.

    1.7k GitHub stars~1.4k tokensUpdated today
    Business, Finance & HRAuto-check passed
  • Opik Online Eval

    comet-ml/opik-mcp

    Take a judge live on production traffic — create an Opik online evaluation rule (LLM-as-judge or Python metric) on a project with sampling, filters, variable mapping, and a cost cap, then confirm…

    220 GitHub stars~3k tokensUpdated today
    AI & LLM EngineeringAuto-check: notes
  • Nevermined Payments

    LeoYeAI/openclaw-master-skills

    Integrates Nevermined payment infrastructure into AI agents, MCP servers, Google A2A agents, and REST APIs.

    2.2k GitHub stars~4.5k tokensUpdated 2 mo ago
    Backend & APIsAuto-check: notes

Questions about LexGuard MCP Developer Guide

What does LexGuard MCP Developer Guide do?

Developer guide for the LexGuard Korean law MCP server: layer rules, adding tools and repositories, JSON-RPC responses, law API handling, answer rules and tests. py`, then to a service, then to a repository that calls the national law API. Routes handle JSON-RPC parsing, SSE streaming and the tool and prompt listings.

When should I use LexGuard MCP Developer Guide?

LexGuard MCP Developer Guide fits situations like: adding a new MCP tool to the LexGuard server; writing a repository that wraps another national law API endpoint; changing the JSON-RPC endpoint or the response formatting; writing tests for services that run without an API key.

How do I install LexGuard MCP Developer Guide in Claude Code?

Run `npx skills add SeoNaRu/lexguard-mcp --skill lexguard-mcp-dev -a claude-code`. Or copy the skill folder (.cursor/skills/lexguard-mcp-dev in SeoNaRu/lexguard-mcp) into .claude/skills/lexguard-mcp-dev in your project. Claude Code loads it when a task matches its description.

How do I install LexGuard MCP Developer Guide in Codex?

Run `npx skills add SeoNaRu/lexguard-mcp --skill lexguard-mcp-dev -a codex`. Or copy the skill folder (.cursor/skills/lexguard-mcp-dev in SeoNaRu/lexguard-mcp) into .agents/skills/lexguard-mcp-dev in your project. Codex loads it when a task matches its description.

Can I use LexGuard MCP Developer Guide in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add SeoNaRu/lexguard-mcp --skill lexguard-mcp-dev -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/lexguard-mcp-dev, .gemini/skills/lexguard-mcp-dev, .github/skills/lexguard-mcp-dev and .opencode/skills/lexguard-mcp-dev in your project.

What does LexGuard MCP Developer Guide need to run?

Going by SKILL.md and its folder, LexGuard MCP Developer Guide needs the command-line tools its instructions call (pytest). Our summary lists: Python with pytest; A key for the Korean national law information API.

Does LexGuard MCP Developer Guide access the network?

SKILL.md contains no URLs. Any network use would come from the scripts or tools the agent runs. This is read from the text; nothing was executed.

Is LexGuard MCP Developer Guide safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. Review the folder before installing.

What licence does LexGuard MCP Developer Guide use?

LexGuard MCP Developer Guide has a licence file (the repository's licence) that doesn't match a standard licence. Read it on GitHub before reusing the skill.

How many tokens does LexGuard MCP Developer Guide use?

About 1.1k tokens (SKILL.md is roughly 4.3k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to LexGuard MCP Developer Guide?

Skills that share tags, products or a category with LexGuard MCP Developer Guide: MCP Server Builder (anthropics/skills, 180k stars), MCP Server Builder (shareAI-lab/learn-claude-code, 78k stars), Python Tests (PrefectHQ/fastmcp, 28k stars) and Tiger Brokers OpenAPI SDK (qusong0627/QuantMind, 1.7k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains LexGuard MCP Developer Guide?

SeoNaRu (a GitHub user) maintains it in SeoNaRu/lexguard-mcp, which has 131 GitHub stars. The repository was last updated on August 11, 2026.

Source: SeoNaRu/lexguard-mcp on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.