criar-mcp-precedente

Generate a standalone MCP server for Brazilian court jurisprudence search.

12|7|Updated Jan 28, 2026
One-click install
npx skills add https://github.com/georgemarmelstein/sistema-marmelstein --skill criar-mcp-precedente
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: criar-mcp-precedente
Source: https://github.com/georgemarmelstein/sistema-marmelstein/tree/main/.claude/skills/criar-mcp-precedente
Command: npx skills add https://github.com/georgemarmelstein/sistema-marmelstein --skill criar-mcp-precedente

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill helps you create a standalone MCP server to search Brazilian court jurisprudence on tribunals that do not expose a usable public REST API, turning fragile web scraping work into a structured, tool-based interface.

Core Features & Use Cases

  • Tribunal endpoint discovery: detects whether the target site is REST-like or requires scraping (JSF/AJAX, HTML parsing) by analyzing the target page and network behavior.
  • Boolean syntax discovery and validation: systematically tests operators (AND/OR/NOT, exact phrases, hyphens, wildcards, proximity) and produces an operator table suitable for the MCP tool docstring.
  • MCP generation with standard tools: generates a standalone server template with the required tools (buscar_, gerar_relatorio_, listar_*), plus a README with installation and usage guidance.

Quick Start

Ask the AI to create a new MCP for your tribunal by providing the jurisprudence search URL and telling it whether to create the MCP in the project’s .claude/mcp-servers or in the global ~/.claude/mcp-servers.

Frequently Asked Questions about criar-mcp-precedente

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I create an MCP server for searching jurisprudence on tribunals without a public REST API?

You can create an MCP server for jurisprudence search by using a Skill that detects tribunal endpoints, analyzes web scraping requirements for JSF/AJAX pages, and generates a standalone server.py with standard buscar_*, gerar_relatorio_*, and listar_* tools.

How do I discover boolean search operators supported by a specific tribunal's jurisprudence search page?

Discover boolean search operators by running systematic empirical testing on the tribunal's search page, validating AND/OR/NOT logic, exact phrases, hyphens, wildcards, and proximity operators to generate a documented operator table for the MCP tool docstring.

Can I generate an MCP server for Brazilian court websites that rely on JSF and AJAX for search?

Yes, you can generate an MCP server for Brazilian court websites relying on JSF and AJAX by analyzing target page network behavior, detecting endpoint requirements, and producing a structured tool-based interface replacing fragile web scraping.

What's the best way to turn tribunal web scraping logic into a structured MCP toolset?

The best way to convert tribunal web scraping logic into a structured MCP toolset is generating a standalone server template with buscar_*, gerar_relatorio_*, and listar_* tools, plus a README with installation guidance and operator documentation.

Does the generated MCP server documentation include boolean operator case sensitivity and wildcard behavior?

Yes, the generated MCP server documentation includes boolean operator case sensitivity and wildcard behavior by documenting the results of empirical syntax testing directly within the MCP tool docstring and README files.

What files are generated when creating a jurisprudence search MCP for a tribunal without an API?

Creating a jurisprudence search MCP generates server.py, requirements.txt, and README.md files containing the standard MCP toolset, boolean operator validation tables, and installation instructions for the target tribunal search page.