mcp_coder
Verified Safeby MarcusJellinghaus
Overview
Automates and orchestrates LLM-assisted software development workflows, including issue planning, code implementation, quality checks, and pull request creation.
Installation
mcp-coder helpEnvironment Variables
- GITHUB_TOKEN
- JENKINS_URL
- JENKINS_USER
- JENKINS_TOKEN
- ANTHROPIC_API_KEY
- VIRTUAL_ENV
- CONDA_PREFIX
Security Notes
Interacts with GitHub and Jenkins via API, and Claude via API/CLI. Credentials (tokens, API keys) are sourced from environment variables or `config.toml` (recommended practice), avoiding hardcoded secrets in source code. Uses `subprocess` for external commands (e.g., git, Claude CLI, formatters, mypy) but these commands are internally constructed, limiting risks of arbitrary command injection. No direct use of `eval` or intentional obfuscation found. The primary security consideration is the user's secure management of API tokens and configuration.
Similar Servers
boost
Laravel Boost accelerates AI-assisted development by providing context and specialized tools for AI to generate high-quality, Laravel-specific code.
claude-code-mcp
Provides an MCP server to allow LLMs to directly invoke Claude Code CLI for complex coding, file system, and Git operations, bypassing interactive permission prompts.
claude-codex-settings
This repository provides a toolkit and configurations for integrating Model Context Protocol (MCP) servers into Claude Code plugins, enabling AI agents to interact with external services, local tools, and APIs within an AI-assisted development environment.
consult-llm-mcp
Facilitates Claude Code to consult powerful external AI models for complex code analysis, debugging, and review tasks.