What is mcp-tw-judgment CLAUDE.md?

A project instruction file for a Taiwan court-judgment search server, including setup, commands, architecture, and tests.

It helps install dependencies, start the server, test its connection and tool registration, run unit tests, and understand where the tools and parsers are located.

It gives coding agents the repository-specific guidance needed to run, modify, and verify the server correctly.

How asgard-ai-platform/mcp-tw-judgment configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to asgard-ai-platform/mcp-tw-judgment. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/asgard-ai-platform/mcp-tw-judgment/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/asgard-ai-platform/mcp-tw-judgment

Made for: Claude Code.

Wrote 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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/asgard-ai-platform/mcp-tw-judgment/claude-md/github.svg)](https://agentmods.dev/instructions/asgard-ai-platform/mcp-tw-judgment/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/asgard-ai-platform/mcp-tw-judgment/claude-md"><img src="https://agentmods.dev/badge/instructions/asgard-ai-platform/mcp-tw-judgment/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/asgard-ai-platform/mcp-tw-judgment/claude-md"><img src="https://agentmods.dev/badge/instructions/asgard-ai-platform/mcp-tw-judgment/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 698 This file is loaded in full into every session.

When invoked 698 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.00698	$0.00698
Opus 5	$0.00349	$0.00349
Sonnet 5	$0.00140	$0.00140
Haiku 4.5	$0.00070	$0.00070

Measured 9d ago against content hash 420703231df7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mcp-tw-judgment CLAUDE.md 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 9d 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.

CLAUDE.md · 60 lines

How it starts

The opening of the file, as written. The whole thing — 60 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.

Overview

MCP server for searching Taiwan judicial judgments via 司法院裁判書系統. Exposes four tools over stdio JSON-RPC 2.0: search_judgments, get_judgment, get_judgment_pdf, and lookup_legal_term.

Commands

# Setup
uv sync

# Run server
uv run mcp-tw-judgment

# Test API connectivity
uv run python scripts/auth/test_connection.py

# Unit tests (no network)
uv run python -m unittest tests.test_judgment_parser -v

# Tool registration tests (no network)
uv run python -m unittest tests.test_all_tools -v

# Live API tests
RUN_LIVE_TESTS=1 uv run python -m unittest tests.test_all_tools -v

After editing mcp_server.py, run uv sync --reinstall-package mcp-tw-judgment to update the installed entry point.

Architecture

stdio (JSON-RPC 2.0)
  → mcp_server.py          side-effect import triggers tool registration
    → app.py               FastMCP singleton
      → tools/judgment_tools.py   @mcp.tool() definitions
          → connectors/rest_client.py   api_get_text() fetches raw HTML; api_get_bytes() for binary downloads
          → parser/judgment_parser.py   pure HTML → structured data
            → config/settings.py        BASE_URL, ENDPOINTS, headers

Key Patterns

Singleton: app.py creates the FastMCP instance; all modules import from it
Side-effect import: mcp_server.py imports tool modules to trigger @mcp.tool() registration
Two-step fetch: search_judgments sends GET /FJUD/qryresult.aspx?akw=… → parses hidQID → fetches GET /FJUD/qryresultlst.aspx?ty=JUDBOOK&q={qid}&page={n} (the iframe content)
Parser layer: parser/judgment_parser.py is pure functions (HTML string in, structured data out). No HTTP calls. Tested offline with fixtures in tests/fixtures/
@live decorator: in tests/test_all_tools.py, wraps unittest.skipUnless(os.environ.get("RUN_LIVE_TESTS"), …)
PDF download: get_judgment_pdf resolves URL via extract_pdf_url(detail_html) (primary) or constructed /FILES/{court}/{rest}.pdf (fallback). Download target chosen by precedence: save_to arg > MCP_TW_JUDGMENT_DOWNLOAD_DIR env > URL-only

Read the full file on GitHub · 60 lines

Changes

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.

9d ago First seen · 60 lines · 698 tokens per session scan A 420703231df7

Subscribe to this mod's changes

mcp-tw-judgment CLAUDE.md is an instructions file published in the GitHub repository asgard-ai-platform/mcp-tw-judgment (0 stars, last pushed 4mo ago), licensed MIT. It adds 698 tokens to every session, about $0.0035 per session on Opus 5. 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.

ai-tools claude judgment judicial legal-tech llm-tools

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

mcp-tw-judgment: Instructions file for Claude Code