Mcp

ai.ragjurv2.5.1更新于 Oct 11, 2026

Brazilian legal search and jurimetria: 115M+ court decisions from 90+ courts across 14 MCP tools.

已验证Streamable HTTP可网页运行网页搜索与抓取数据与分析知识与记忆

概览

AI 生成的概览

让助手检索超过 1.12 亿份巴西法院裁判文书，并进行结果预测、引用核验等法律计量分析。

功能
RAGJur 通过远程 MCP 服务器提供 14 个工具，用于巴西法律检索。工具包括按法院、案件类别和日期筛选的裁判文书全文检索、语义相似检索、主题概览与结果比例、审判庭分歧、判例演变、统计结果预测、审理时长统计、法官与审判庭画像、主题聚类、引用核验、基于检索结果的问答，以及依据真实先例起草程序文书。覆盖 STF、STJ、TST、TSE、TCU 以及联邦、州、劳动、选举和审计法院。
适用场景
适合巴西法律检索与法律计量分析：查找先例、核验引用是否存在、比较审判庭、估计结果或审理时长，以及依据检索到的裁判文书起草文书。
运行要求
远程 streamable HTTP 端点 mcp.ragjur.ai，无需本地运行时或软件包。认证方式为 OAuth 2.1（PKCE S256，scope ragjur:read），或可选使用 RAGJur API 密钥并通过 x-api-key 请求头发送。API 密钥随 RAGJur 订阅提供。需要能访问该远程服务器的网络。
安装前请注意
x-api-key 请求头携带在 RAGJur 账户面板创建的 RAGJur API 密钥（rj_…），应视为机密。查询内容会发送到第三方服务器 mcp.ragjur.ai，由其检索语料库并返回结果；该服务器被描述为无状态、会话 TTL 为 30 分钟，数据在巴西处理。起草与核验工具生成的法律内容应由具备资质的专业人士复核。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Mcp，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "mcp": {
      "type": "http",
      "url": "https://mcp.ragjur.ai/mcp"
    }
  }
}

README

RAGJur — Claude Plugin

Brazilian legal RAG for Claude — search 112M+ court decisions from 90+ Brazilian tribunals.

This repository contains the Claude plugin manifest for RAGJur. The plugin connects Claude to the RAGJur MCP server (remote, streamable HTTP) at https://mcp.ragjur.ai/mcp.

Install

In Claude Code:

/plugin marketplace add btechbrasil/ragjur-mcp/plugin install ragjur@btechbrasil

During installation, Claude asks for your RAGJur API Key (stored as a sensitive user config — it is never read from your machine without asking). API keys are included with RAGJur subscriptions: ragjur.ai.

What you get — 14 tools

ToolWhat it does
buscar_jurisprudenciaFull-text search over 112M+ decisions (BM25, filters by tribunal/class/date)
similaridadeSemantic search — decisions similar to a case or ementa (embeddings)
panorama_temaTopic overview: outcome rate, result categories, trend
divergencia_turmasDivergence between panels/chambers on a topic
evolucao_jurisprudencialHow a thesis evolved over time (quarterly)
predicao_resultadoStatistical outcome prediction with confidence interval
tempo_tramitacaoLitigation-time statistics (median, percentiles)
perfil_relatorJudge/rapporteur profile on a topic
dna_turmaStatistically characteristic terms of a panel
clusters_tematicosCluster a topic into sub-issues
estrategia_juizFull strategic analysis of a judge for a topic
verificar_citacaoAnti-hallucination citation verification
chat_juridicoQ&A grounded on retrieved decisions
gerar_pecaDraft a procedural document grounded on real precedents

Coverage

STF, STJ, TST, TSE, TCU, all TRFs (1–6), all state courts (TJs), labor courts (TRTs), electoral courts, state audit courts (TCEs) and administrative tax appeal tribunals (CARF/DRJs/TARFs) — 112 million+ decisions and growing daily.

Example prompts

  • "Busque os acórdãos mais recentes do STJ sobre busca e apreensão em alienação fiduciária"
  • "Qual a taxa de provimento de recursos sobre dano moral no TJSP? Há divergência entre as câmaras?"
  • "Verifique se as citações desta peça existem"
  • "Redija uma contestação sobre despejo por falta de pagamento, lado réu, TJMG"

How it works

The plugin registers one remote MCP server (HTTP transport). Your queries are sent to mcp.ragjur.ai, which searches the Elasticsearch corpus and returns grounded results. The server is stateless — no conversation or query data is persisted after the session ends.

Privacy & data

  • Stateless MCP server (30-minute session TTL, nothing stored)
  • Data processed in Brazil (Alibaba Cloud São Paulo region)
  • LGPD-compliant: ragjur.ai/lgpd
  • Privacy policy: ragjur.ai/privacidade

Support

License

MIT (this repository — plugin manifest and documentation). The RAGJur service is a commercial product of Beans Tech.

来源：README.md，提交 36e1f1b

工具

0
工具元数据尚未被收录。

版本历史

1
  1. v2.5.1最新Oct 11, 2026