criar-mcp-precedente

criar-mcp-precedente is a skill for Claude Code from georgemarmelstein/superjurista-dev. It costs 141 tokens per session (6,091 once invoked), scanned A, original, MIT.

Um guia para criar servidores MCP que pesquisam decisões judiciais em tribunais sem uma API pública documentada. MCP é um formato que permite conectar essas pesquisas a ferramentas de inteligência artificial.

In plain words
What is it for?
Serve para criar uma pesquisa de jurisprudência por scraping, analisar arquivos HAR, descobrir consultas com operadores de busca e conectar o servidor ao projeto.
Why use it?
Sites de tribunais podem usar formulários complexos, JavaScript ou APIs internas em vez de uma API simples. O guia orienta a descobrir como o site funciona e registrar o servidor no projeto.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: reads .claude/ paths; names the AskUserQuestion tool.

Part of the superjurista-dev plugin — 11 skills, 22 commands, 7 agents shipped together

Good fit Serve para criar uma pesquisa de jurisprudência por scraping, analisar arquivos HAR, descobrir consultas com operadores de busca e conectar o servidor ao projeto.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/georgemarmelstein/superjurista-dev/criar-mcp-precedente
Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Any agent
npx skills add georgemarmelstein/superjurista-dev --skill criar-mcp-precedente
Clone the repo
git clone --depth 1 https://github.com/georgemarmelstein/superjurista-dev

Made for: Claude Code.

Or install superjurista-dev, the plugin that ships this one along with the rest of its 11 skills, 22 commands, 7 agents.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for criar-mcp-precedente

README.md
[![agentmods](https://agentmods.dev/badge/skills/georgemarmelstein/superjurista-dev/criar-mcp-precedente/github.svg)](https://agentmods.dev/skills/georgemarmelstein/superjurista-dev/criar-mcp-precedente)
Your own site
<a href="https://agentmods.dev/skills/georgemarmelstein/superjurista-dev/criar-mcp-precedente"><img src="https://agentmods.dev/badge/skills/georgemarmelstein/superjurista-dev/criar-mcp-precedente/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for criar-mcp-precedente

Your own site · 80×15
<a href="https://agentmods.dev/skills/georgemarmelstein/superjurista-dev/criar-mcp-precedente"><img src="https://agentmods.dev/badge/skills/georgemarmelstein/superjurista-dev/criar-mcp-precedente.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 141 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 6,091 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00141 $0.06091
Opus 5 $0.00071 $0.03045
Sonnet 5 $0.00028 $0.01218
Haiku 4.5 $0.00014 $0.00609

Measured 11d ago against content hash 5c97be67f686, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, from the pricing page.

Security

Grade A, and why

criar-mcp-precedente scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 11d ago.

The scan reads SKILL.md. This mod also ships 1 executable file (references/template-server.py), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skills/criar-mcp-precedente/SKILL.md · 520 lines

How it starts

The opening of the file, as written. The whole thing — 520 lines — stays where its author put it; the contents beside it link to each section on GitHub.

criar-mcp-precedente

<quando_usar> Use quando: - Usuário quer criar MCP para tribunal sem API documentada - Precisa fazer scraping de página de jurisprudência - Quer descobrir sintaxe booleana de um tribunal - Tribunal usa JSF/AJAX ou formulários complexos

### 0.1 Coletar URL do tribunal
Solicitar ao usuário a URL da página de busca de jurisprudência.

### 0.2 Perguntar localização do MCP
Usar AskUserQuestion:
```
Onde deseja criar o MCP?

1. Projeto atual (.claude/mcp-servers/[nome]/)
   → Disponível apenas neste projeto

2. Global (~/.claude/mcp-servers/[nome]/)
   → Disponível em todos os projetos

3. Diretório customizado
   → Informar caminho
```

Em qualquer opção, o arquivo pode viver onde o usuário preferir — o que ativa o MCP
é o REGISTRO no `.mcp.json` da raiz do projeto, com caminho ABSOLUTO do server.py
(ver Fase 3.4). NÃO registrar em settings.json: config de MCP ali é padrão antigo
e quebra silenciosamente (o servidor simplesmente não aparece).

### 0.3 Analisar tipo de API
Usar WebFetch na URL para detectar:

**Sinais de API REST aberta (→ recomendar mcp-builder):**
- Documentação Swagger/OpenAPI visível
- Endpoints /api/v1/ retornando JSON puro
- Headers CORS permissivos
- Sem ViewState/CSRF tokens

**Sinais de scraping necessário (→ continuar):**
- Formulários JSF (javax.faces.ViewState)
- AJAX com tokens CSRF
- Respostas em HTML/XML parcial
- Session cookies obrigatórios

**Sinais de bloqueio insuperável (→ abortar ou Chrome MCP):**
- reCAPTCHA v3 invisível (script google.com/recaptcha com `size=invisible`)
- reCAPTCHA v2 (checkbox "Não sou um robô")
- hCaptcha ou outros CAPTCHAs comportamentais
- Cloudflare Bot Protection

### 0.4 Decisão de roteamento

**Se API REST aberta detectada:**
```
"Detectei uma API REST documentada. Recomendo usar a skill mcp-builder.

Repositório: https://github.com/anthropics/anthropic-tools

Deseja que eu instale a mcp-builder?"
```

**Se CAPTCHA por requisição detectado (reCAPTCHA v3/v2, hCaptcha):**
```
"Este portal exige um token de CAPTCHA a cada busca — bloqueio insuperável
para um MCP server em Python puro.

Opções:
1. SKILL via Chrome MCP (rota comprovada) — em vez de MCP server, criar uma
   skill que roda a busca DENTRO do navegador real: o CAPTCHA gera o token
   normalmente porque há um Chrome de verdade. Modelo vivo:
   .claude/skills/jurisprudencia-eleitoral (SJUR/TSE, hCaptcha invisível,
   token de uso único por requisição, hcaptcha.reset() + retry).
2. Endpoints parcialmente abertos — antes de desistir, verificar se PARTE da
   superfície dispensa CAPTCHA (no TSE, o download do inteiro teor em PDF é
   aberto: só a busca é protegida). Um MCP híbrido pode cobrir a parte aberta.
3. Desistir — portal inviável.

O CAPTCHA comportamental analisa mouse, teclado e tempo, e gera tokens que
não podem ser replicados programaticamente."
```

Read the full file on GitHub · 520 lines

Files

What ships with it

5 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 11d ago First seen · 520 lines · 141 tokens per session scan A 5c97be67f686

Subscribe to this mod's changes

criar-mcp-precedente is a skill published in the GitHub repository georgemarmelstein/superjurista-dev (22 stars, last pushed 1mo ago), licensed MIT. It adds 141 tokens to every session and 6,091 once invoked, about $0.0007 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other skills, from other repositories

specification-writing

A workflow for writing complete patent specifications from patent claims and an invention disclosure. It adapts the document to a chosen jurisdiction, such as the US, Europe, or China.

wanshuiyin/Auto-claude-code-research-in-sleep · 49 tokens

regulatory-research-fallback

Fallback workflow for regulatory research when web extraction tools fail on government PDFs.

HKUDS/OpenSpace · 20 tokens

x-scorecard

OpenSSF Scorecard for assessing open source project security. Check security best practices and compliance. Dependency: This is an x-cmd module. Install x-cmd first (see x-cmd skill for installation options). see x-cmd skill for installation.

x-cmd/x-cmd · 57 tokens

gesellschaftsrechtliche-satzungen-agb

Für Gesellschaftsrechtliche Satzungen AGB Abgrenzung: ordnet Norm, Beweislast und Gegenargument; Ergebnis: Prüfprodukt mit Risiko und nächstem Schritt. Fachgebiet: AGB-Recht-Prüfer. Route: gesellschaftsrechtliche-satzungen-agb.

Klotzkette/claude-fuer-deutsches-recht · 69 tokens

memstack-business-gdpr

Use this skill when the user says 'GDPR', 'data protection', 'privacy compliance', 'DPA', 'DSAR', 'data subject request', 'cookie consent', 'privacy audit', 'CCPA', or asks 'do I need GDPR for this repo'. Scans the repository to detect what personal data is collected, classifies sensitivity, determines whether GDPR…

cwinvestments/memstack · 121 tokens

nda-review

Use when the user uploads or pastes a non-disclosure agreement and asks for review, redline, risk assessment, or a recommendation on whether to sign. Identifies missing standard protections, one-sided or unusual provisions, and operational issues; produces a structured report with severity ratings and citations to…

LegalQuants/lq-ai · 79 tokens