mcpac
by sh1nduu
Overview
Empowers AI agents to interact with Model Context Protocol (MCP) servers by generating type-safe TypeScript/JavaScript interfaces for their tools and providing a secure execution environment.
Installation
No command providedSecurity Notes
This tool executes arbitrary TypeScript/JavaScript code, which can interact with the host system's filesystem, network, and resources. It explicitly warns against running untrusted code and highlights the risks of MCP servers themselves. While it includes a capability-based permission system (`--grant` flags) to control tool access, it remains a high-risk tool if misused. Use with extreme caution and only with trusted code.
Similar Servers
mcp-use
A comprehensive framework for building full-stack Model Context Protocol (MCP) applications, including AI agents, MCP servers with UI widgets, and integrated debugging tools in both Python and TypeScript.
agentx
A unified CLI tool for managing MCP (Model Context Protocol) servers and skills across multiple AI coding agents like Claude Code, Codex, Cursor, Gemini CLI, and OpenCode.
context-engine
Provides an agent-agnostic local context engine via Model Context Protocol (MCP) for coding agents, enabling semantic search, planning, code review, and prompt enhancement with AI integration.
mcp-execution
Transforms any Model Context Protocol (MCP) server into executable, type-safe TypeScript tools for AI agents, enabling progressive loading and achieving significant token savings.