Wenshucha Court Judgments

Search 160M+ Chinese court judgment records and verify citations.

CommunityOnlineAPI key requiredGlobalFreeCan modify data

What it can do

  • Search Judgments: 在 1.6 亿条中国裁判文书记录的标题与库内正文中检索。返回案号、标题、法院、裁判日期、命中片段，以及从判决全文【尽力解析】的原告、被告、精确诉讼角色、裁判结果片段（最多 400 字符）（plaintiff/defendant/party_roles/referee_result，非权威，抽不到为 null 或空数组）。完整公司/机构名会自动使用 phrase；
  • Get Judgment: 按案号取库内正文。案号全角半角括号均可。库内正文不是模型摘要；部分长文最多保留前 6,000 字。返回的 struct 里有从正文【尽力解析】的原告/被告/精确诉讼角色/裁判结果片段（最多 400 字符；非权威，抽不到则缺省）。同一案号有多条记录时，会在全部命中记录中按正文长度排序，优先返回较完整的一条；duplicate_records 是该案号的记录数。
  • Verify Case Number: 【反幻觉】核验一个案号是否真实存在。存在则返回标题、法院、裁判日期作为溯源凭证。用途：当你或用户引用了某个案号，调用本工具确认它不是编造的。重要：返回 not_found 只代表【本库】查不到，不代表该判决在现实中不存在。本库有 160,291,678 条记录，但记录数不等于案件数，且不是中国全部裁判文书。

What data it sees

Do you need an account

An API key from the service settings is required

Search 160M+ Chinese court judgment records and verify citations.

  • search_judgments — keyword search over titles and full texts; filter by year range, court, province. Use match_mode: "phrase" for company or person names.
  • get_judgment — fetch the stored full text by case number.
  • verify_case_number — anti-hallucination: check whether a cited case number actually exists.
  • verify_quote — anti-hallucination: check whether a quoted passage really appears in a judgment.

Lexical (BM25) search, not vector search: rewrite colloquial phrasing into legal terms and query in Simplified Chinese (Traditional characters return 0 hits). Every response carries a _coverage block with data caveats and a _quota block with remaining usage.

Free public key wsc_demo_public works out of the box (20 searches and 5 full texts per IP per day). More quota: https://www.wenshucha.com/pricing/ — operated by Shenzhen Xingpu Network Technology Co., Ltd.

How to connect

How to connect Wenshucha Court Judgments to Claude

The server address to paste into Claude settings:

https://judgments--wenshucha.run.tools

  1. Open Claude (claude.ai or the desktop app).
  2. Go to Settings → Connectors.
  3. Click Add custom connector.
  4. Paste the server address copied below into Remote MCP server URL and click Add.
  5. In a chat, click + → Connectors and switch the new connector on.

Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.

Authorization

After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.

How to connect Wenshucha Court Judgments to ChatGPT

The server address to paste into ChatGPT settings:

https://judgments--wenshucha.run.tools

  1. Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
  2. Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
  3. Open Settings → Connectors and click Create.
  4. Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
  5. Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
  6. In a new chat open + → Apps/Connectors and enable the connector.

OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.

Authorization

On first use ChatGPT opens the service's sign-in window. Sign in and approve access.

How to connect Wenshucha Court Judgments to Cursor

The server address to paste into Cursor settings:

https://judgments--wenshucha.run.tools

Fastest: click Open in Cursor below and confirm the prompt.

Manually:

  1. In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
  2. Paste the JSON copied below into ~/.cursor/mcp.json (per project: .cursor/mcp.json in the repo root).
  3. Save the file. The server appears in the MCP list; authorize it there if asked.

Authorization

If the service needs sign-in, an authorize button appears next to the server in the MCP list.

Server tool list (4)

Raw names from tools/list. Only developers need these.

search_judgments在 1.6 亿条中国裁判文书记录的标题与库内正文中检索。返回案号、标题、法院、裁判日期、命中片段，以及从判决全文【尽力解析】的原告、被告、精确诉讼角色、裁判结果片段（最多 400 字符）（plaintiff/defendant/party_roles/referee_result，非权威，抽不到为 null 或空数组）。完整公司/机构名会自动使用 phrase；按简称或人名查诉讼时，请显式传 match_mode:"phrase"，避免召回只共用个别汉字的无关主体。库内正文不是模型摘要；部分长文最多保留前 6,000 字。每条结果带 has_body（是否有可取的判决正文）与 body_chars；有正文的记录已优先排前，要读全文请对 has_body=true 的记录调 get_judgment，has_body=false 的记录库内只有元信息（老批次缺正文或调解结案不公开）。可按年份区间、法院名称、省份收窄。⚠️ 本工具是【精确词汇检索】(BM25)，不是向量语义检索。调用前你必须：①把口语表述改写为法律术语再检索（「老板不发工资」→「拖欠劳动报酬」，两者都能查到东西，但法律术语的命中量高出约两个数量级，且结果相关性远好于口语）；②查询词必须用【简体中文】——繁体字检索会直接命中 0 条，因为分词器不处理繁体；③多个词之间是 AND 关系，词越多结果越少；关键概念建议给 2–3 个同义表述分别检索后合并。
get_judgment按案号取库内正文。案号全角半角括号均可。库内正文不是模型摘要；部分长文最多保留前 6,000 字。返回的 struct 里有从正文【尽力解析】的原告/被告/精确诉讼角色/裁判结果片段（最多 400 字符；非权威，抽不到则缺省）。同一案号有多条记录时，会在全部命中记录中按正文长度排序，优先返回较完整的一条；duplicate_records 是该案号的记录数。
verify_case_number【反幻觉】核验一个案号是否真实存在。存在则返回标题、法院、裁判日期作为溯源凭证。用途：当你或用户引用了某个案号，调用本工具确认它不是编造的。重要：返回 not_found 只代表【本库】查不到，不代表该判决在现实中不存在。本库有 160,291,678 条记录，但记录数不等于案件数，且不是中国全部裁判文书。
verify_quote【反幻觉】核验一段判词能否以分词后的连续短语命中库内正文。可选传 caseNo 把核验范围锁定到某一份判决（回答「这段话真的是这个案子里说的吗」）。用途：核查代理意见、法律意见书里引用的判词是否被改写或编造。注意：核验会忽略标点与空白，但受中文分词边界影响；使用完整句核验最稳定。转述、增删或替换实词可能判为未命中。