DataJud (CNJ)

io.github.mcp-dirPublished by GitHub account mcp-dirv0.1.1Updated Oct 24, 2026

Public lookup of Brazilian court cases (metadata + docket) via the CNJ/DataJud API. Free, no login.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingKnowledge & Memory

Overview

AI-generated overview

Lets an assistant look up public Brazilian court cases by CNJ number, tribunal, class, subject, and docket movements.

What you can do
Connects to the public CNJ/DataJud API to retrieve metadata and docket movements for Brazilian court cases. Tools include lookup of a case by CNJ number and tribunal, search by class, judging body, or subject with pagination, a movement timeline, a raw Elasticsearch query escape hatch, and a locator that reports which instance a case is currently in, including whether it reached TST or STJ. Read-only.
When to use it
Useful when an assistant needs to answer questions about public Brazilian litigation: finding a case by its CNJ number, checking recent docket activity, searching cases by class or subject, or determining the current instance of a case. Not for confidential or sealed proceedings.
Requirements
Remote MCP endpoint over HTTP; no login, credentials, or API key declared. Works with any MCP client that supports MCP over HTTP. Network access required.
Before you install
Read-only, but returned case data is sent to whichever LLM host you connect, described as a sub-processor outside the provider's control; plans with training opt-out are recommended. Only publicly available DataJud records are returned; sealed cases do not appear. The hosted server itself is proprietary.

Installation

In SourceWeft

  1. Open DataJud (CNJ) in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.mcp-dir%2Fdatajud-mcp/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "datajud-cnj": {
      "type": "http",
      "url": "https://api.mcp.ai/p_datajud"
    }
  }
}

README

This repository has no README.

Tools

11

datajud_get_processo

Busca processo por número CNJ e tribunal. Retorna `tribunal`, `total`, `count` e `processos[]` (metadados e movimentações por instância). Só sem resultados inclui `ausencia`. Aceita número com ou sem máscara. Quando `processos` está vazio, `ausencia` traz o motivo provável (numero_invalido | tribunal_divergente | nao_publicado | carga_ausente | indeterminado) e a explicação. Com resultados, esse bloco não é retornado. Leia esse bloco antes de repetir a consulta em outra tool: a API pública do CNJ não publica processo em segredo de justiça, então `nao_publicado` NÃO significa que o processo não existe. O processo que sobe por recurso MANTÉM o número da origem: o AIRR/RR de um processo do TRT continua com o número do TRT no índice `tst` (e o REsp de TJ/TRF no `stj`). Quando o 2º grau registra esse recurso, a resposta inclui `instancia_superior`; para ver em que instância o processo está agora, use datajud_localizar_processo.

Parameterstribunalrequirednumero_processorequired

datajud_movimentos

Consulta movimentações por número CNJ e tribunal. Retorna `tribunal`, `numeroProcesso` e `instancias[]` (timeline e metadados). Só sem resultados inclui `ausencia`. Ideal para detectar movimentação nova. Quando `instancias` está vazio, `ausencia` traz o mesmo diagnóstico de datajud_get_processo (motivo provável + explicação). Com resultados, esse bloco não é retornado. Quando o 2º grau registra recurso ao tribunal superior (recurso de revista/AIRR → TST, recurso especial → STJ), inclui `instancia_superior` com o próximo passo: o processo mantém o mesmo número lá.

Parameterstribunalrequirednumero_processorequired

datajud_raw_query

Avançado: envia uma query Elasticsearch crua pro índice do tribunal (escape hatch). `query` é SÓ a cláusula de busca (ex.: { match: { "classe.nome": "Apelação" } }); size, sort, _source e search_after vão nos campos próprios. Use search_after (valor `sort` do último hit) pra paginar além de 10.000 resultados. A API pública do CNJ é lenta em índices grandes: prefira size pequeno e `_source` com só os campos que precisa.

Parametersfromsizesortqueryrequired_sourcetribunalrequiredsearch_after

datajud_localizar_processo

Localiza em que instância o processo está agora, só pelo número CNJ: consulta a origem e o tribunal superior (TRT → TST, TJ/TRF → STJ). O tribunal de origem é derivado do número e os dois índices são consultados em paralelo. Retorna `instancias[]` ordenadas (1º grau → 2º grau → superior) com tribunal, grau, classe, órgão julgador e último movimento, `instancia_mais_recente` e `consultas[]` (status de cada índice consultado). Consulta processual trabalhista no TST: o processo que sobe ao TST (recurso de revista, AIRR) MANTÉM o número do TRT de origem, então consultar só o TRT nunca mostra a fase no TST. Se um índice falhar, `consultas[]` traz o erro dele e o outro resultado continua valendo. Sem nenhum resultado, inclui `ausencia` (mesmo diagnóstico de datajud_get_processo). O STF não está no DataJud. Para a timeline completa de uma instância, use datajud_movimentos com o `tribunal` dela.

Parametersnumero_processorequired

show_version

Show Version

Show the current MCP platform and adapter versions.

Takes no parameters.

report_bug

Report Bug

Report a bug, missing feature, or send feedback. Include the conversation array with recent messages for reproduction.

Parameterscontextmessagerequiredconversation

connect

Connection Status

Returns connection status and URLs. When all providers are connected, returns authenticated:true and empty pending[]. When credentials are missing, returns connect_url for the toolkit and per-install URLs.

Takes no parameters.

toolkit_info

Toolkit Info

Returns the current toolkit state: installed MCPs, their connection status, the accounts connected to each one, and how many catalog tools each exposes.

Takes no parameters.

marketplace

Marketplace

The official mcp.ai marketplace — the in-platform catalog of every MCP/tool, AND the way to run them. Covers capability requests like "find an MCP that does X", "consulta um CPF", "is there a tool for Y". Core flow: action=search discovers MCPs by intent → describe returns one MCP's full profile (every tool with its id + params, pricing, auth) so you pick the right tool_id → invoke RUNS that tool. KEY: invoke works even when the MCP is NOT installed — it runs the tool pontualmente (one-off), without adding the MCP to the toolkit and without bloating the tool list. If the MCP needs a credential/login, invoke returns a connect link; if it is paid and the wallet is empty, invoke returns a checkout/top-up link (the user opens it, then you retry). Use install only to make an MCP PERMANENT in the active toolkit (its tools then show up natively in future sessions); prefer invoke for a single/occasional use. list_tools lists what is callable right now. subscribe/cancel handle per-MCP billing; report_bug sends feedback; request_mcp asks us to build a NEW MCP when nothing fits. Search/describe flag installed_in_toolkit vs installed_in_workspace. Writes (install/uninstall/subscribe/cancel and the one-off install behind invoke) require workspace owner/admin. It also carries the mcp.ai PROMPT LIBRARY, which is about ready-made prompt TEXT rather than MCPs: search_prompts finds one, get_prompt returns its full text with {{variables}} filled, and publish_prompt saves a prompt and returns a shareable mcp.ai/p/<slug> link that opens without login.

Parameterslimitqueryactionmcp_idmessagetool_idargumentsimmediatetier_slugprompt_bodyprompt_slugprompt_tool+11 more

authenticate

Authenticate

MCP.AI for IDE agents (Cursor, etc.): log in in the browser, copy the access token. Best: add it to this server's config as a header `Authorization: Bearer <token>` for a permanent, non-expiring connection. Or paste it here for a session-only login: call with { token: "<jwt>" } after the user pastes, or with no args to get the link.

Parameterstoken

Version history

2
  1. v0.1.1LatestOct 7, 2026
  2. v0.1.0Sep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.