convez.ai
MCP ServerAutomaçãoAvançado
SDGLBL

MCP Claude Code

SDGLBL/mcp-claude-code

MCP server com Claude Code capabilities para manipulação e análise de código

Ver no GitHub
BomPluginScore · de 0 a 100

Servidor MCP que replica as capacidades do Claude Code, permitindo que Claude execute operações de leitura, escrita e modificação de código diretamente em projetos. Implementa ferramentas completas para análise de código, busca com ripgrep, edição de arquivos e notebooks Jupyter, além de suporte a agentes delegados para tarefas complexas.

Instalação

$npx convez-ai SDGLBL/mcp-claude-code

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
305
Forks
39
Acompanhando
1
Saúde
42%
Último commit
há 1 ano
Versão
v0.5.1
Issues abertas
7
Contribuidores
4

Casos de uso

  • Integrar Claude Code em clientes MCP personalizados
  • Automatizar refatoração e modificação de bases de código
  • Buscar e analisar padrões em projetos grandes com ripgrep
  • Editar notebooks Jupyter programaticamente via Claude
  • Delegar tarefas complexas a sub-agentes especializados

Veredito

Implementação sólida e completa do protocolo MCP com ferramentas robustas para manipulação de código. Ideal para quem precisa integrar capacidades de edição de código em workflows automatizados, mas requer conhecimento técnico de MCP e configuração de agentes LLM.

README

A tradução para o português deste README ainda está na fila.

MCP Claude Code

An implementation of Claude Code capabilities using the Model Context Protocol (MCP).

Overview

This project provides an MCP server that implements Claude Code-like functionality, allowing Claude to directly execute instructions for modifying and improving project files. By leveraging the Model Context Protocol, this implementation enables seamless integration with various MCP clients including Claude Desktop.

example

Features

  • Code Understanding: Analyze and understand codebases through file access and pattern searching
  • Code Modification: Make targeted edits to files with proper permission handling
  • Enhanced Command Execution: Run commands and scripts in various languages with improved error handling and shell support
  • File Operations: Manage files with proper security controls through shell commands
  • Code Discovery: Find relevant files and code patterns across your project with high-performance searching
  • Agent Delegation: Delegate complex tasks to specialized sub-agents that can work concurrently
  • Multiple LLM Provider Support: Configure any LiteLLM-compatible model for agent operations
  • Jupyter Notebook Support: Read and edit Jupyter notebooks with full cell and output handling

Tools Implemented

ToolDescription
readRead file contents with line numbers, offset, and limit capabilities
writeCreate or overwrite files
editMake line-based edits to text files
multi_editMake multiple precise text replacements in a single file operation with atomic transactions
directory_treeGet a recursive tree view of directories
grepFast pattern search in files with ripgrep integration for best performance (docs)
content_replaceReplace patterns in file contents
grep_astSearch code with AST context showing matches within functions, classes, and other structures
run_commandExecute shell commands (also used for directory creation, file moving, and directory listing)
notebook_readExtract and read source code from all cells in a Jupyter notebook with outputs
notebook_editEdit, insert, or delete cells in a Jupyter notebook
thinkStructured space for complex reasoning and analysis without making changes
dispatch_agentLaunch one or more agents that can perform tasks using read-only tools concurrently
batchExecute multiple tool invocations in parallel or serially in a single request
todo_writeCreate and manage a structured task list
todo_readRead a structured task list

Getting Started

For detailed installation and configuration instructions, please refer to INSTALL.md.

For detailed tutorial of 0.3 version, please refer to TUTORIAL.md

Security

This implementation follows best practices for securing access to your filesystem:

  • Permission prompts for file modifications and command execution
  • Restricted access to specified directories only
  • Input validation and sanitization
  • Proper error handling and reporting

Development

To contribute to this project:

  1. Fork the repository
  2. Create a feature branch (git checkout -b feature/amazing-feature)
  3. Commit your changes (git commit -m 'Add some amazing feature')
  4. Push to the branch (git push origin feature/amazing-feature)
  5. Open a Pull Request

License

This project is licensed under the MIT License - see the LICENSE file for details.

Ver o original no GitHub

Bom para

Relacionados