MCP Manager for Claude Desktop
LocalAbout MCP Manager for Claude Desktop
MCP Manager for Claude Desktop is a simple web interface for managing MCP servers in the macOS Claude desktop app. It is aimed at users who want to set up servers without editing configuration by hand, and it states that it runs entirely client-side.
Key features
- 01Manages MCP servers for the Claude desktop app
- 02Quick setup for many popular MCP servers
- 03Configuration of environment variables and server settings
- 04One-click copying of terminal install commands
- 05Built with React, TypeScript and Vite
Use cases
- 01Adding MCP servers to the Claude desktop app on macOS
- 02Setting up common servers through a web form instead of editing files
MCP support
The project is a configuration interface for MCP servers used by the Claude desktop app, helping users add and set up servers.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEMCP Manager for Claude Desktop
A simple web GUI to manage Model Context Protocol (MCP) servers for the Claude Desktop app on MacOS easily. Just follow the instructions and paste a few commands to give your Claude app instant superpowers.

What is MCP?
The Model Context Protocol (MCP) enables Claude to access private data, APIs, and other services to answer questions and perform actions on your behalf. Learn more about MCP at:
Features
- 🚀 Easy-to-use interface for managing MCP servers
- 🔒 Runs entirely client-side - your data never leaves your computer
- ⚡️ Quick setup for popular MCP servers:
- Apple Notes - Access and search your Apple Notes
- AWS Knowledge Base - Access and query AWS Knowledge Base for information retrieval
- Brave Search - Search the web with Brave Search API
- Browserbase - Let Claude explore the web with Browserbase
- Cloudflare - Manage your Cloudflare workers and account resources
- Everart - Interface with Everart API for digital art and design tools
- Exa - Search the web with Exa
- Filesystem - Access and manage local filesystem
- GitHub - Access your GitHub repositories
- GitLab - Manage GitLab repositories and resources
- Google Drive - Access and search files in your Google Drive
- Google Maps - Access Google Maps API for location services
- Memory - Give Claude memory of previous conversations
- Obsidian - Read and search files in your Obsidian vault
- Perplexity - Search the web with Perplexity API
- PostgreSQL - Connect and interact with PostgreSQL databases
- Puppeteer - Automate browser interactions
- Sequential Thinking - Enable step-by-step reasoning
- Slack - Access your Slack workspace
- SQLite - Manage SQLite databases
- Todoist - Access and search your Todoist tasks
- YouTube Transcript - Access and search YouTube transcripts
- 🛠 Simple configuration of environment variables and server settings
- 📋 One-click copying of terminal commands for installation
Tech Stack
- Frontend Framework: React 18 with TypeScript
- Build Tool: Vite
- Styling:
- TailwindCSS for utility-first CSS
- DaisyUI for component styling
- Tiempos Font to match the Anthropic Design Language
- Package Manager: Bun
- Deployment: Cloudflare Pages for <60s build times
Project Structure
src/
├── components/ # React components
│ ├── server-configs/ # Server-specific configuration components
│ └── ...
├── assets/ # Static assets and fonts
├── App.tsx # Main application component
├── server-configs.ts # MCP server configurations
└── utils.ts # Utility functions
Development
-
Install dependencies:
bun install -
Start the dev server:
bun dev -
Build for production:
bun run build
Contributing
Contributions are extremely welcome! Please open a PR with new MCP servers or any other improvements to the codebase. PS. I wasnt able to get fetch, time, and sentry working, if you can help me out, that would be great!
Disclaimer
This project is not affiliated with Anthropic. All logos are trademarks of their respective owners.
License
Apache 2.0
Contact us for custom AI automation solutions and product development.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.