SinoVerdict MCP Server

SinoVerdict MCP Server

Enables AI assistants to search and analyze over 1.1 million structured Chinese labor dispute judgments, providing class cases, statistics, and source links.

Category
Visit Server

README

文书查 / SinoVerdict MCP Server

110 万+ 结构化的中国劳动争议判决接进你的 AI 助手 / Agent —— Codex、Claude Desktop、Cursor、Claude Code,或任何支持 MCP 的客户端。

Beta 阶段限劳动争议数据集;正式版开放 1.5 亿份全量裁判文书 + 法规库。 申请试用 key:邮件 chenjiaxin@wenshucha.com 或电话 131-6872-7779,一个工作日内回复。


提供的 Tool

Tool 用途
search_cases 案情文本 + 结构化过滤(省份/案由/解雇原因/工龄/年份)→ Top 20 类案 + 金额分位(p25/中位/p75)+ 胜诉率 + 关键裁判因素
get_case 依 doc_id 取单条判决详情
case_stats 按省份 / 解雇原因 / 工龄分桶切片聚合统计

每条判决均含中国裁判文书网原文链接(source_url),结果可溯源、可呈堂


安装(三步)

# 1. 拉代码
git clone https://github.com/jack0752168/wenshucha-mcp.git ~/wenshucha-mcp

# 2. 装依赖(只需一次)
cd ~/wenshucha-mcp && npm install

# 3. 先用 curl 验证 key 通(把 <KEY> 换成你的试用 key)
curl -H "X-API-Key: <KEY>" "https://tob.wenshucha.com/api/v1/health"
# 返回 {"ok":true,...} 即 key 有效

接入 Codex(OpenAI Codex CLI)

方式一:命令行一行加(推荐)

codex mcp add wenshucha \
  --env WENSHUCHA_API_KEY=<你的试用KEY> \
  --env WENSHUCHA_API_BASE=https://tob.wenshucha.com \
  -- node $HOME/wenshucha-mcp/bin/wenshucha-mcp.mjs

加完确认:

codex mcp list          # 应能看到 wenshucha
codex mcp get wenshucha

方式二:手动写 ~/.codex/config.toml

[mcp_servers.wenshucha]
command = "node"
args = ["/Users/<你>/wenshucha-mcp/bin/wenshucha-mcp.mjs"]

[mcp_servers.wenshucha.env]
WENSHUCHA_API_KEY = "<你的试用KEY>"
WENSHUCHA_API_BASE = "https://tob.wenshucha.com"

在 Codex 里怎么用

启动 codex,直接用自然语言让它调,例如:

用 wenshucha 检索「经济性裁员 工龄7年 拒签合同」在广东省的类案,给我金额区间和胜诉率。

Codex 会自动调用 search_cases,拿回 Top 20 类案 + 量化统计 + 裁判文书网原文链接。


接入 Claude Desktop

编辑 ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "wenshucha": {
      "command": "node",
      "args": ["/Users/<你>/wenshucha-mcp/bin/wenshucha-mcp.mjs"],
      "env": {
        "WENSHUCHA_API_KEY": "<你的试用KEY>",
        "WENSHUCHA_API_BASE": "https://tob.wenshucha.com"
      }
    }
  }
}

重启 Claude Desktop 后,模型侧自动看到 search_cases / get_case / case_stats 三个 tool。

接入 Cursor

~/.cursor/mcp.json:

{
  "mcpServers": {
    "wenshucha": {
      "command": "node",
      "args": ["/Users/<你>/wenshucha-mcp/bin/wenshucha-mcp.mjs"],
      "env": {
        "WENSHUCHA_API_KEY": "<你的试用KEY>",
        "WENSHUCHA_API_BASE": "https://tob.wenshucha.com"
      }
    }
  }
}

接入 Claude Code

claude mcp add wenshucha \
  --env WENSHUCHA_API_KEY=<你的试用KEY> \
  --env WENSHUCHA_API_BASE=https://tob.wenshucha.com \
  -- node /Users/<你>/wenshucha-mcp/bin/wenshucha-mcp.mjs

环境变量

变量 默认 说明
WENSHUCHA_API_KEY (无) 必填,试用 key
WENSHUCHA_API_BASE https://tob.wenshucha.com 选填,换 staging 时用

试用限制

  • 60 次/分钟 per key
  • Beta 阶段限「劳动争议」数据集
  • Trial key 90 天有效,正式合作后换长期 key

联络

文书查 · 深圳星谱网络科技有限公司 商务电话:131-6872-7779 邮箱:chenjiaxin@wenshucha.com 官网:https://www.wenshucha.com

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured