Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

DataJud (CNJ)

REMOTE · API.MCP.AI · SCANNED SEP 25

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

Available components

0 this week 76 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security63
Transport & Reachability100
Schema Quality & AI Usability65
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1413 tokens (~141/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 10 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Install

How do I install the DataJud (CNJ) MCP server?

DataJud (CNJ) is a hosted endpoint at https://api.mcp.ai/p_datajud, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · api.mcp.ai

# add to Claude Code
claude mcp add --transport http mcp-dir-datajud-mcp 'https://api.mcp.ai/p_datajud'
// .cursor/mcp.json
{
  "mcpServers": {
    "mcp-dir-datajud-mcp": {
      "url": "https://api.mcp.ai/p_datajud"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "mcp-dir-datajud-mcp": {
      "type": "http",
      "url": "https://api.mcp.ai/p_datajud"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.mcp-dir-datajud-mcp]
url = "https://api.mcp.ai/p_datajud"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "mcp-dir-datajud-mcp": {
      "type": "remote",
      "url": "https://api.mcp.ai/p_datajud",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add mcp-dir-datajud-mcp --url 'https://api.mcp.ai/p_datajud' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  mcp-dir-datajud-mcp:
    url: "https://api.mcp.ai/p_datajud"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "mcp-dir-datajud-mcp": {
      "Transport": "http",
      "Url": "https://api.mcp.ai/p_datajud"
    }
  }
}
# add to Vellum
assistant mcp add mcp-dir-datajud-mcp -t streamable-http -u 'https://api.mcp.ai/p_datajud'
// mcp.json
{
  "mcpServers": {
    "mcp-dir-datajud-mcp": {
      "type": "http",
      "url": "https://api.mcp.ai/p_datajud"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 14 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 0.9.346 → 0.9.351 functional
  • 10 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 0.9.345 → 0.9.346 functional
  • 9 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “datajud_get_processo” rewrote its description, which is the text the model reads security
    • Tool “datajud_movimentos” rewrote its description, which is the text the model reads security
    • Server version: 0.9.343 → 0.9.345 functional
  • 7 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 0.9.341 → 0.9.343 functional
  • 6 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 0.9.340 → 0.9.341 functional
  • 5 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 0.9.339 → 0.9.340 functional
  • 3 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Server version: 0.9.332 → 0.9.339 functional
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 25 Sept 2026 · Probed https://api.mcp.ai/p_datajud

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=mcp.ai CN=WE1,O=Google Trust Services,C=US 31 Jul 2026 29 Oct 2026 ECDSA 256 ECDSA-SHA256 796a3b1f576e3f2e133c5d19d8f7be3b
SANs: mcp.ai, *.mcp.ai
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of api.mcp.ai. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 3799 8 Verified
mcp.ai. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://api.mcp.ai/p_datajud Verified 200
http (plaintext) http://api.mcp.ai/p_datajud Inconclusive 406
MCP tools · 10 exposed · ~1,284 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
authenticate ~99

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.

NameTypeReqDescription
tokenstring––

No output schema declared.

No examples provided.

connect ~42

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.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

datajud_get_processo ~177

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.

NameTypeReqDescription
numero_processostringyes–
tribunalstringyes–

No output schema declared.

No examples provided.

datajud_movimentos ~115

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.

NameTypeReqDescription
numero_processostringyes–
tribunalstringyes–

No output schema declared.

No examples provided.

datajud_raw_query ~78

Avançado: envia um corpo de query Elasticsearch cru pro índice do tribunal (escape hatch). Use search_after pra paginar além de 10k.

NameTypeReqDescription
fromnumber––
query–yes–
search_after–––
sizenumber––
sort–––
tribunalstringyes–

No output schema declared.

No examples provided.

datajud_search ~137

Busca processos em um tribunal por classe, órgão julgador e/ou assunto (códigos das tabelas do CNJ), paginada e ordenada por data de ajuizamento. DataJud NÃO indexa nome de parte nem OAB — pra isso use o MCP djen/escavador.

NameTypeReqDescription
assunto_codigonumber––
classe_codigonumber––
fromnumber––
numero_processostring––
orgao_julgador_codigonumber––
sizenumber––
sort_descboolean––
tribunalstringyes–

No output schema declared.

No examples provided.

marketplace ~532

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.

NameTypeReqDescription
actionstring––
argumentsstring––
cancel_commentstring––
cancel_reasonstring––
conversationstring––
immediateboolean––
limitnumber––
mcp_idstring––
messagestring––
prompt_bodystring––
prompt_categorystring––
prompt_descriptionstring––
prompt_slugstring––
prompt_targetsarray––
prompt_titlestring––
prompt_toolstring––
prompt_varsstring––
querystring––
report_contextstring––
request_detailsstring––
request_namestring––
tier_slugstring––
tool_idstring––

No output schema declared.

No examples provided.

report_bug ~50

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

NameTypeReqDescription
contextstring––
conversationstring––
messagestringyes–

No output schema declared.

No examples provided.

show_version ~17

Show the current MCP platform and adapter versions.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

toolkit_info ~37

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

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Common questions

What is the DataJud (CNJ) MCP server?

DataJud (CNJ) is an MCP server listed in the public MCP registry as io.github.mcp-dir/datajud-mcp. Public lookup of Brazilian court cases (metadata + docket) via the CNJ/DataJud API. Free, no login. This page covers its hosted endpoint (https://api.mcp.ai/p_datajud).

Is the DataJud (CNJ) MCP server safe to use?

DataJud (CNJ) scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the DataJud (CNJ) MCP server expose?

DataJud (CNJ) exposes 10 tools: datajud_get_processo, datajud_search, datajud_movimentos, datajud_raw_query, show_version, and 5 more. Their descriptions and schemas cost roughly 1,284 tokens of context every time the server is loaded.

Does the DataJud (CNJ) MCP server require authentication?

No. We connected to DataJud (CNJ) without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the DataJud (CNJ) MCP server still maintained?

DataJud (CNJ) is still listed as active in the MCP registry. We last reached this channel on 25 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.