案例文书 - 案例语义检索接口 根据自然语言 query 在案例库中进行语义相似度检索，默认同时覆盖普通案例和权威案例，支持通过 wenshu_filter 按案件类别、案由、文书类型、法院、地域、结案日期及典型案例等条件过滤，并返回整理后的完整案例内容（不等同于原始裁判文书逐字全文）及相似度评分。 HTTP POST https://open.chineselaw.com/open/case_vector_search 接口文档: https://apiplatform.legalmind.cn/api/apis/16 未在 schema 中精确建模的参数也可以直接传入。
AI agents call yuandian_case_vector_search to retrieve information from Yuandian without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | Yes | 待检索问题 / 查询文本 |
return_num | number | — | 返回案例数量（默认为45，最大不超过检索回的案例总数） |
rewrite_flag | boolean | — | 是否对查询做改写，默认为true |
wenshu_filter | object | — | 案例检索过滤条件，详细内容见字段说明 |
Parameters from the server's own tool schema.
This is a search/query tool that retrieves legal case documents and information from a database based on semantic similarity. It supports filtering and returns structured case content with scores. The operation is read-only with no side effects—it queries an existing database without creating, modifying, or deleting data.
From the tool's definition Tool description states '案例语义检索接口' (case semantic search interface) that performs search/retrieval '根据自然语言 query 在案例库中进行语义相似度检索' (semantic similarity search in case database based on natural language query).
Attacks that exploit this kind of access
案例文书 - 案例语义检索接口 根据自然语言 query 在案例库中进行语义相似度检索，默认同时覆盖普通案例和权威案例，支持通过 wenshu_filter 按案件类别、案由、文书类型、法院、地域、结案日期及典型案例等条件过滤，并返回整理后的完整案例内容（不等同于原始裁判文书逐字全文）及相似度评分。 HTTP POST https://open.chineselaw.com/open/case_vector_search 接口文档: https://apiplatform.legalmind.cn/api/apis/16 未在 schema 中精确建模的参数也可以直接传入。. It is categorised as a Read tool in the Yuandian MCP Server, which means it retrieves data without modifying state.
yuandian_case_vector_search accepts 4 parameters: query, return_num, rewrite_flag, wenshu_filter. Required: query. The full parameter table on this page comes from the server's own tool schema.
Register the Yuandian MCP server in PolicyLayer and add a rule for yuandian_case_vector_search: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Yuandian. Nothing to install.
yuandian_case_vector_search is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the yuandian_case_vector_search rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for yuandian_case_vector_search. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
yuandian_case_vector_search is provided by the Yuandian MCP server (yuandian-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →