No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
by aa0101181514 · MCP Server · ★ 323
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
🔒 Is tw-legal-rag safe to install? View the security audit →
Taiwan Legal RAG () 🌐 Language / 語言 / 言語 English ・ 繁體中文 ・ 日本語 Open-source CLI for semantic Taiwan legal judgment retrieval, powered by Legal Detective's 22M-judgment retrieval infrastructure. Taiwan Legal RAG CLI retrieves Taiwan court judgments from Legal Detective's public TLR endpoint and packages them for use with your own AI tools. It does not generate legal advice, does not call any LLM, and does not guarantee semantic faithfulness of third-party model outputs. Its built-in citation check only verifies whether cited judgments belong to the retrieved bundle. Why it is different This is not a generic keyword judgment search tool. It connects to the TLR retrieval service that Legal Detective has been building for a long time: About 22 million Taiwan court decisions, structurally processed and vectorized. Thousands of hours of retrieval pipeline optimization. Semantic fuzzy search — not limited to docket numbers, court names, or keywords; you can use natural language to find judgments that are "conceptually similar but worded differently." Exact docket lookup (v1.1) — when the query is a complete Taiwan docket number (e.g.
| Stars | 323 |
| Forks | 42 |
| Language | Python |
| Category | MCP Server |
| Quality Score | 72.7373026375402/100 |
| Open Issues | 1 |
| Last Updated | 2026-09-23 |
| Created | 2026-05-23 |
| Platforms | claude-code, cli, codex, mcp, python |
| Est. Tokens | ~17k |
Looking for a tw-legal-rag alternative? If you're comparing tw-legal-rag with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
MCP server that lets Claude Code and other AI agents read and search large PDFs, one file or a whole folder: a
Open library of legal AI skills (SKILL.md) for MCP-compatible agents — 18,000+ skills, 54 jurisdictions, 410+
Structural code intelligence for AI agents — semantic search, knowledge graphs, and a built-in MCP server in o
Local-first RAG server for developers. Semantic + keyword search for code and technical docs. Works with MCP o
🦀 Prevents outdated Rust code suggestions from AI assistants. This MCP server fetches current crate docs, use
中国法条与法律法规检索 Agent Skill｜Chinese legal research Agent Skill for retrieving and verifying Chinese laws from offi
Explore other popular mcp server tools:
tw-legal-rag is 台灣法律 MCP 伺服器 + CLI（免費、免註冊、免 API key）：2,250 萬筆裁判書、行政函釋、憲法法庭裁判，附引用查核。Free Taiwan legal MCP server for Claude/ChatGPT/Codex — bring your own LLM, retrieval-only.. It is categorized as a MCP Server with 323 GitHub stars.
tw-legal-rag is primarily written in Python. It covers topics such as claude-mcp, court-judgments, legal-ai.
You can find installation instructions and usage details in the tw-legal-rag GitHub repository at github.com/aa0101181514/tw-legal-rag. The project has 323 stars and 42 forks, indicating an active community.
The top alternatives to tw-legal-rag on Agent Skills Hub include pdf-mcp, legal-skills-open, octocode. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: