catalyst_builder
by Yapade0708
Overview
Build AI-powered integrations for Claude and ChatGPT using YAML configuration, enabling automation of business processes for databases, REST APIs, and cloud services.
Installation
No command providedEnvironment Variables
- API_BASE_URL
- API_TOKEN
- DB_HOST
- DB_PORT
- DB_NAME
- DB_USER
- DB_PASSWORD
- SSH_HOST
- SSH_USER
- SSH_KEY_PATH
Security Notes
The system is designed to execute user-defined code (Python/JavaScript transforms) and system commands (SSH tools). It uses `subprocess.run` for Docker deployments and `shutil` for local file operations. While `PackValidator` performs structural validation and `TransformConfig` has a `sandbox` flag, the strength of this sandboxing or comprehensive input sanitization for command execution is not evident in the provided source. This creates a significant attack surface for potential command injection or arbitrary code execution if a malicious 'Knowledge Pack' is deployed, possibly leading to compromise of the host system or Docker container.
Similar Servers
consult-llm-mcp
Facilitates Claude Code to consult powerful external AI models for complex code analysis, debugging, and review tasks.
vibes
Vibes transforms Claude Desktop into a conversational development environment through distributed MCP servers, allowing users to describe what they want to build and have Claude implement it while teaching them.
rest-to-mcp-adapter
Transforms REST API specifications (OpenAPI, Swagger, OpenAPI Actions) into Model Context Protocol (MCP) tools, enabling AI agents like Claude and GPT to interact with any REST API.
MCP-Council
Automates the conversion of any REST API into a Model Context Protocol (MCP) server, enabling AI assistants to interact with external APIs through a standardized interface.