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 full-stack framework for building Model Context Protocol (MCP) servers, MCP clients, and AI agents in both Python and TypeScript, supporting interactive UI widgets and robust debugging.
agentor
Deploy scalable AI agents with tool integrations (weather, email, GitHub, etc.) and support for A2A and MCP communication protocols.
mmcp
Manages Model Context Protocol (MCP) server definitions in a central configuration and applies them to various AI agent tools.
mcp
A TypeScript SDK for building and interacting with Model Context Protocol (MCP) servers, facilitating AI agent interaction through exposed tools, prompts, and resources via JSON-RPC over HTTP/SSE.