mcp-desk
@debsouryadatta
About mcp-desk
A Desktop Application To Interact With Your MCP Servers
Basic information
Config
No standard config provided
This server doesn't expose a parseable MCP config block in its README. See the repository for install instructions.
RepositoryTools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is mcp-desk?
MCP Desk is a desktop application built with Electron, React, and TypeScript that serves as a client for interacting with Multi-Capability Platform (MCP) servers. It provides a chat interface for AI agents powered by Langchain and OpenRouter models, along with settings management for MCP configurations and the ability to import/export application data.
How to use mcp-desk?
Download the latest pre‑built release for your OS from GitHub, or clone the repository and run pnpm install followed by pnpm run dev for development. After launching, navigate to the settings section to input your MCP server details and select an LLM model, then use the chat interface to interact with the AI agent. Settings can be backed up or restored using the import/export functionality.
Key features of mcp-desk
- Cross‑platform desktop app (Windows, macOS, Linux)
- Modern UI built with React, TypeScript, Shadcn UI, and Tailwind CSS
- MCP client using the
easy-mcp-uselibrary - AI agent chat powered by Langchain and OpenRouter models
- Supports tool‑calling with selected LLM models
- Settings management with JSON import/export via localStorage
- Renders assistant messages in Markdown format
Use cases of mcp-desk
- Connect to and manage multiple MCP server configurations through a graphical interface
- Chat with an AI agent that can use tools provided by connected MCP servers
- Backup and restore application settings (MCP configurations and model preferences) as JSON files
- Experiment with different LLM models from OpenRouter within an integrated chat environment
FAQ from mcp-desk
What is mcp-desk?
MCP Desk is a desktop application that acts as a client for Multi-Capability Platform (MCP) servers. It offers a chat interface for AI agents, settings management, and the ability to import/export configurations.
How do I install mcp-desk?
You can download a pre‑built installer from the GitHub Releases page (.dmg for macOS, .exe for Windows) or build from source by cloning the repository, installing dependencies with pnpm, and running pnpm run dev or one of the build commands.
What are the prerequisites for development?
You need Node.js and the pnpm package manager installed globally. The project uses Electron, React, TypeScript, and various libraries listed under “Built With”.
How do I build mcp-desk for Linux?
Run pnpm run build:linux after completing the installation steps. Pre‑built Linux packages are not currently provided in the releases, so Linux users must build the application locally.
Where are my settings stored?
Application settings are stored in the browser’s localStorage. You can back up or restore them via the import/export feature, which creates or reads a JSON file.
More Other MCP servers
FastMCP v2 🚀
jlowin🚀 The fast, Pythonic way to build MCP servers and clients.
Blender
ahujasidOpen-source MCP to use Blender with any LLM
🚀 Model Context Protocol (MCP) Curriculum for Beginners
microsoftThis open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
ghidraMCP
LaurieWiredMCP Server for Ghidra
Activepieces
activepiecesAI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents
Comments