build-mcpb

Package a local MCP server with its runtime into a .mcpb bundle.

Updated Dec 17, 2024
One-click install
npx skills add https://github.com/LAF-US/IDAHO-VAULT --skill build-mcpb-laf-us
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: build-mcpb
Source: https://github.com/LAF-US/IDAHO-VAULT/tree/main/.claude/plugins/marketplaces/claude-plugins-official/plugins/mcp-server-dev/skills/build-mcpb
Command: npx skills add https://github.com/LAF-US/IDAHO-VAULT --skill build-mcpb-laf-us

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

MCPB packages a local MCP server with its runtime into a single, installable bundle so users can run an MCP server without installing Node or Python.

Core Features & Use Cases

  • Bundles the MCP server, runtime, and manifest into a .mcpb package for offline distribution.
  • Supports Node or Python runtimes and hosts runtime dependencies inside the bundle.
  • Ideal for desktop apps, OS integrations, and distribution where external toolchains are unavailable.

Quick Start

Package a local MCP server into a self-contained .mcpb bundle for immediate deployment.

Frequently Asked Questions about build-mcpb

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I package a local MCP server for offline distribution without Node or Python installed?

Package a local MCP server for offline distribution by bundling the server code, its runtime, and the manifest into a single .mcpb file. This allows the server to run on machines where no Node or Python toolchain is installed.

What is an .mcpb bundle and when do I need it for desktop app integration?

An .mcpb bundle is a self-contained package that embeds an MCP server and its runtime. You need it for desktop app integration or OS integrations where external toolchains are unavailable or you want to distribute offline MCP servers.

Can I bundle both Node and Python runtimes into a single MCP server package?

You can bundle either a Node or Python runtime into an .mcpb package. The packaging workflow hosts the dependencies for the chosen runtime inside the bundle, ensuring the local MCP server runs without external toolchain installations.

What's the best way to distribute a local MCP server across different operating systems?

The best way to distribute a local MCP server across different operating systems is using a repeatable packaging workflow to create a .mcpb bundle, which encapsulates the manifest and appropriate runtime for cross-platform distribution.

Does packaging an MCP server with its runtime require any external dependencies on the target machine?

Packaging an MCP server with its runtime into an .mcpb bundle requires no external dependencies on the target machine. The bundle hosts all runtime dependencies internally, making it ideal for offline distribution and environments without toolchains.