Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/lawchat-oss/mcp-taiwan-legal-dbWrote 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.
[](https://agentmods.dev/mcp/lawchat-oss/mcp-taiwan-legal-db/taiwan-legal-db)<a href="https://agentmods.dev/mcp/lawchat-oss/mcp-taiwan-legal-db/taiwan-legal-db"><img src="https://agentmods.dev/badge/mcp/lawchat-oss/mcp-taiwan-legal-db/taiwan-legal-db/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.
<a href="https://agentmods.dev/mcp/lawchat-oss/mcp-taiwan-legal-db/taiwan-legal-db"><img src="https://agentmods.dev/badge/mcp/lawchat-oss/mcp-taiwan-legal-db/taiwan-legal-db.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
taiwan-legal-db 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 12d 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.
What it actually says
{
"taiwan-legal-db": {
"command": ".venv/bin/python",
"args": [
"-m",
"mcp_server.server"
]
}
}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.
- 12d ago First seen · 9 lines scan A c88f21a8ad2e
taiwan-legal-db is an MCP server published in the GitHub repository lawchat-oss/mcp-taiwan-legal-db (190 stars, last pushed 19d ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. 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 2026-08-30.
Other mcp servers, from other repositories
turk-hukuku-ictihat-mcp
Türk yargı kararlarını (Yargıtay/Bölge Adliye + Danıştay + AYM bireysel başvuru) yapay zekâ araçlarına açan MCP sunucusu. Runs locally from the turk-hukuku-ictihat-mcp Python package.
turk-hukuku-mevzuat-mcp
Türk mevzuatının resmî güncel metnini (mevzuat.gov.tr) yapay zekâ araçlarına açan MCP sunucusu. Runs locally from the turk-hukuku-mevzuat-mcp Python package.
mcp-saos
MCP server for Polish court judgments via the SAOS API with verifiable citations. Runs locally from the @matematicsolutions/mcp-saos npm package.
bidda-compliance
MCP server "bidda-compliance", hosted remotely at bidda.com, as configured in Bidda-Ai/bidda-mcp.
swiss-legal-mcp
MCP server "swiss-legal-mcp" as configured in cotadavidch-ctrl/swiss-legal-mcp-public. Runs locally from the swiss-legal-mcp npm package.
mcp-krs
MCP server for the Polish KRS company registry via the official Ministry of Justice API. Runs locally from the @matematicsolutions/mcp-krs npm package.