Sandbox
@eugenepyvovarov/MCPbundler

macOS app for MCP servers and agent skills

MCP Bundler gives you a native macOS interface for managing local MCP servers, remote endpoints, and skill sources. It also runs in headless stdio mode so you can wire it into CLI and automation workflows.

47 stars9 forksSwiftUpdated 6mo ago
Who it's for

Builders who manage MCP servers and agent skills across a macOS app and CLI workflows.

What it delivers

You can keep agent skills and MCP servers organized in one tool and run them from the desktop or automation scripts.

What it does

Manage local and remote MCP servers

The app provides a native macOS UI for adding, viewing, and operating local MCP servers and remote endpoints.

Headless stdio runner

It can run without the UI so CLI tools and automation workflows can talk to it over stdio.

Skill marketplace sources

It includes curated sources for browsing and installing skills.

OAuth and remote auth support

The codebase includes OAuth flows and remote authentication work for secured endpoints.

README

MCP Bundler (macOS)

MCP Bundler is a macOS SwiftUI app for managing and running Agent Skills and Model Context Protocol (MCP) servers, with a headless stdio mode for CLI and automation workflows. The codebase targets the MCP lifecycle spec baseline dated 2025-06-18.

Status

I decided to move the project from Paid software to open source thanks to Bags platform I need some time to prepare the code for open sourcing it and for allowing to download builds straight from the site and remove license gate. Bear with me, I need some hours for this.

Until then you can download app here: TEMP DOWNLOAD LINK

Features

  • Manage local MCP servers and remote endpoints from a native macOS UI.
  • Headless stdio runner for scripting and tool integrations.
  • Skill marketplace sources with curated defaults.
  • OAuth flows and remote auth support (work in progress).

Screenshots

MCP Servers view Servers list with folders, health status, and quick actions.

Skills library Skills library with folders and per-location toggles.

Project settings Project settings for skill sync locations, marketplaces, and optimizations.

Project logs Project logs with auto-refresh controls and pagination.

Skills marketplace Skills marketplace browser with categories and install actions.

Requirements

  • macOS
  • Xcode (latest stable)

Contributing

PRs should describe changes, list tests run, and link relevant spec sections or issues.

Code of Conduct

Be respectful and constructive. By participating, you agree to follow the GitHub Community Guidelines.

Security

Please use GitHub Security Advisories for sensitive disclosures. Do not file public issues for security vulnerabilities.

Support

Open a GitHub issue with clear steps to reproduce, logs, and screenshots where relevant.

License

Apache-2.0. See LICENSE.

Files in the repo

Repository payload13 top-level entries
  • .github
  • docs
  • MCPBundler
  • MCPBundler.xcodeproj
  • MCPBundlerTests
  • scripts
  • .gitignore
  • AGENTS.md
  • CHANGELOG.md
  • LICENSE
  • MCPBundler.xctestplan
  • NOTICE
  • README.md

Discussion (0)

Ask about usage, or say what you built with it

Sign in to join the discussion.

No comments yet. Be the first to say what this is good for.

More tools

JuliusBrussee/
caveman

🪨 why use many token when few token do trick — Claude Code skill that cuts 65% of tokens by talking like caveman

105k
1 add
MemPalace/
mempalace

The best-benchmarked open-source AI memory system. And it's free.

59k
stablyai/
orca

Orca is the ADE for working with a fleet of parallel agents. Run any coding agent with your own subscription. Available on desktop, mobile and remote runtime.

66k

A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io

132k

Never stop coding. Free MIT AI gateway: one endpoint, 352 providers (150+ free), 1200+ models Kimi, Claude, GPT, Gemini, GLM, DeepSeek, MiniMax. Works with Claude Code, Codex, Cursor, OpenCode, Cline & Copilot. Quota-aware auto-fallback, RTK+Caveman compression saves 15-95% tokens, MCP/A2A, Desktop/PWA. Built by 550+ contributors

64k
headroomlabs-ai/
headroom

Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

71k