SinoVerdict MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| WENSHUCHA_API_KEY | Yes | 试用key,必填 | |
| WENSHUCHA_API_BASE | No | 选填,换staging时用 | https://tob.wenshucha.com |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_casesA | 檢索中國勞動爭議裁判文書(110 萬+ 結構化判例),返回高相似度案件 + 金額分位數(p25/中位/p75) + 關鍵裁判因素。支援案情文本 + 結構化過濾(省份/案由/解雇原因/工齡/年份)混合檢索。每條結果含中國裁判文書網原文連結(2026-07-22 實測 3/3 非空),含 body_excerpt 摘要但不含判決全文(要全文用 search_judgments_full 或 browse_full_corpus)。口徑注意:① |
| get_caseA | 依 doc_id 取單條判決詳情。只接受兩種來源的 doc_id:①search_cases / search_judgments 返回的 32 位十六進制;②search_judgments_full(fulltext)返回的 |
| case_statsA | 按 dimension 切片回傳勞動爭議判例聚合統計。讀的是倉庫內預計算快照(8 萬條勞動爭議樣本, |
| search_judgmentsA | 全案由通用檢索:在 120 萬+ 中國裁判文書(覆蓋 1200+ 案由,如民間借貸/買賣合同/信用卡/機動車交通事故/勞動爭議/刑事等)中按關鍵詞 + 結構化條件檢索,返回標題/法院/案由/日期/案號 + 中國裁判文書網原文連結(2026-07-22 實測 20/20 非空)。不返回判決全文(body_text 0/20),要全文用 search_judgments_full 或 browse_full_corpus。 |
| browse_full_corpusA | 全量裁判文書瀏覽(真全量,非樣本):直連完整裁判文書庫,按省份(+案由)左前綴瀏覽最新判決,返回標題/案號/案由/法院/省份/審判程序/裁判日期 + 判決全文 body_text + 中國裁判文書網原文連結。這是目前唯一每條都同時帶全文與原文連結的工具(2026-07-22 實測廣東 20/20 條 source_url 與 body_text 均非空),客戶要「必須可回鏈核驗」的樣本時優先走本工具。口徑注意:① |
| search_judgments_fullA | 全量類案檢索(真全量):按關鍵詞(標題)+ 省份 + 案由 + 法院 + 年份範圍跨集合檢索,返回標題/案號/案由/法院/省份/審判程序/裁判日期 + 判決全文 body_text。比 browse_full_corpus 多了關鍵詞/法院/年份過濾。⚠️本工具的 |
| case_analyticsA | 案件大數據統計(對標法寶「案件大數據」):全庫實時聚合,2026-07-22 實測 year 維度 60 個桶合計 1.51 億條、主體覆蓋 1985–2025(非早期文檔寫的「4580萬 / 2020-2023」,該口徑已作廢)。dim=cause(案由分布)/province(地域分布)/year(年份趨勢)/court(法院排行),可疊加 province / cause / 年份過濾。返回 [{key,count}]。這是唯一能給真實全庫計數的工具——case_stats 的 n_cases 是 8 萬快照裡的抽樣條數,比體量必須用本工具。口徑注意:year 維度含極少量入庫髒桶(如「1014」「209」「2027」,15 個桶合計 1,257 條 = 0.0008%),回答年份趨勢時忽略即可,別當真實年份引用。 |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/jack0752168/wenshucha-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server