Mcp

ai.ragjurv2.5.1更新於 Oct 11, 2026

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

已驗證Streamable HTTP可網頁執行Web Search & Scraping Data & Analytics Knowledge & Memory

概覽

AI 產生的概覽

讓助理檢索超過 1.12 億份巴西法院裁判書，並進行結果預測、引用查核等法律計量分析。

功能: RAGJur 透過遠端 MCP 伺服器提供 14 項工具，用於巴西法律檢索。工具包括可依法院、案件類別與日期篩選的裁判書全文檢索、語意相似檢索、主題概覽與結果比例、審判庭分歧、判例演變、統計結果預測、審理時間統計、法官與審判庭剖析、主題分群、引用查核、以檢索結果為依據的問答，以及根據真實先例起草程序文書。涵蓋 STF、STJ、TST、TSE、TCU 以及聯邦、州、勞動、選舉與審計法院。
適用情境: 適合巴西法律檢索與法律計量分析：尋找先例、查核引用是否存在、比較審判庭、估計結果或審理時間，以及根據檢索到的裁判書起草文書。
執行需求: 遠端 streamable HTTP 端點 mcp.ragjur.ai，不需要本機執行環境或套件。驗證方式為 OAuth 2.1（PKCE S256，scope ragjur:read），或可選用 RAGJur API 金鑰並透過 x-api-key 標頭傳送。API 金鑰隨 RAGJur 訂閱提供。需要能連線至該遠端伺服器的網路。

安裝前請注意

x-api-key 標頭攜帶在 RAGJur 帳戶面板建立的 RAGJur API 金鑰（rj_…），應視為機密。查詢內容會傳送至第三方伺服器 mcp.ragjur.ai，由其檢索語料庫並回傳結果；該伺服器被描述為無狀態、工作階段 TTL 為 30 分鐘，資料在巴西處理。起草與查核工具產生的法律內容應由具備資格的專業人士複核。

安裝

在 SourceWeft 中

開啟儀表板中的 Mcp，將其新增到工作區。
為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。遠端服務在工作區中設定後即可從網頁執行環境執行。

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "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:

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

Tool	What it does
`buscar_jurisprudencia`	Full-text search over 112M+ decisions (BM25, filters by tribunal/class/date)
`similaridade`	Semantic search — decisions similar to a case or ementa (embeddings)
`panorama_tema`	Topic overview: outcome rate, result categories, trend
`divergencia_turmas`	Divergence between panels/chambers on a topic
`evolucao_jurisprudencial`	How a thesis evolved over time (quarterly)
`predicao_resultado`	Statistical outcome prediction with confidence interval
`tempo_tramitacao`	Litigation-time statistics (median, percentiles)
`perfil_relator`	Judge/rapporteur profile on a topic
`dna_turma`	Statistically characteristic terms of a panel
`clusters_tematicos`	Cluster a topic into sub-issues
`estrategia_juiz`	Full strategic analysis of a judge for a topic
`verificar_citacao`	Anti-hallucination citation verification
`chat_juridico`	Q&A grounded on retrieved decisions
`gerar_peca`	Draft 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

Site: ragjur.ai
API docs: api.ragjur.ai
Contact: [email protected]

License

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

來源：README.md，提交 36e1f1b

工具

工具後設資料尚未被收錄。

版本歷史

v2.5.1最新Oct 11, 2026

Mcp

概覽

安裝