Desktop Extensions: One-click local MCP server installation in desktop apps
Desktop Extensions (.dxt
) are zip archives containing a local MCP server and a manifest.json
that describes the server and its capabilities. The format is spiritually similar to Chrome extensions (.crx
) or VS Code extensions (.vsix
), enabling end users to install local MCP servers with a single click.
This repository provides three components: The extension specification in MANIFEST.md, a CLI tool for creating extensions (see CLI.md), and the code used by Claude for macOS and Windows to load and verify DXT extensions (src/index.ts).
Claude for macOS and Windows uses the code in this repository to enable single-click installation of local MCP servers, including a number of end user-friendly features - such as automatic updates, easy configuration of MCP servers and the variables and parameters they need, and a curated directory. We are committed to the open ecosystem around MCP servers and believe that its ability to be universally adopted by multiple applications and services has benefits developers aiming to connect AI tools to other apps and services. Consequently, weโre open-sourcing the Desktop Extension specification, toolchain, and the schemas and key functions used by Claude for macOS and Windows to implement its own support of Desktop Extensions. It is our hope that the dxt
format doesnโt just make local MCP servers more portable for Claude, but other AI desktop applications, too.
At the core, DXT are simple zip files containing your entire MCP server and a manifest.json
. Consequently, turning a local MCP server into an extension is straightforward: You just have to put all your required files in a folder, create a manifest.json
, and then create an archive.
To make this process easier, this package offers a CLI that helps you with the creation of both the manifest.json
and the final .dxt
file. To install it, run:
npm install -g @anthropic-ai/dxt
dxt init
. This command will guide you through the creation of a manifest.json
.dxt pack
to create a dxt
file.You can find the full spec for the manifest.json
and all its mandatory and optional fields in MANIFEST.md. Examples for extensions can be found in examples.
AI tools like Claude Code are particularly good at creating desktop extensions when informed about the spec. When prompting an AI coding tool to build an extension, briefly explain what your extension aims to do - then add the following context to your instructions.
I want to build this as a Desktop Extension, abbreviated as "DXT". Please follow these steps:
- Read the specifications thoroughly:
- https://github.com/anthropics/dxt/blob/main/README.md - DXT architecture overview, capabilities, and integration patterns
- https://github.com/anthropics/dxt/blob/main/MANIFEST.md - Complete extension manifest structure and field definitions
- https://github.com/anthropics/dxt/tree/main/examples - Reference implementations including a "Hello World" example
- Create a proper extension structure:
- Generate a valid manifest.json following the MANIFEST.md spec
- Implement an MCP server using @modelcontextprotocol/sdk with proper tool definitions
- Include proper error handling, security measures, and timeout management
- Follow best development practices:
- Implement proper MCP protocol communication via stdio transport
- Structure tools with clear schemas, validation, and consistent JSON responses
- Make use of the fact that this extension will be running locally
- Add appropriate logging and debugging capabilities
- Include proper documentation and setup instructions
- Test considerations:
- Validate that all tool calls return properly structured responses
- Verify manifest loads correctly and host integration works
Generate complete, production-ready code that can be immediately tested. Focus on defensive programming, clear error messages, and following the exact DXT specifications to ensure compatibility with the ecosystem.
A manifest.json
is the only required file.
extension.dxt (ZIP file)
โโโ manifest.json # Required: Extension metadata and configuration
โโโ server/ # Server files
โ โโโ index.js # Main entry point
โโโ node_modules/ # Bundled dependencies
โโโ package.json # Optional: NPM package definition
โโโ icon.png # Optional: Extension icon
โโโ assets/ # Optional: Additional assets
extension.dxt (ZIP file)
โโโ manifest.json # Required: Extension metadata and configuration
โโโ server/ # Server files
โ โโโ main.py # Main entry point
โ โโโ utils.py # Additional modules
โโโ lib/ # Bundled Python packages
โโโ requirements.txt # Optional: Python dependencies list
โโโ icon.png # Optional: Extension icon
extension.dxt (ZIP file)
โโโ manifest.json # Required: Extension metadata and configuration
โโโ server/ # Server files
โ โโโ my-server # Unix executable
โ โโโ my-server.exe # Windows executable
โโโ icon.png # Optional: Extension icon
Python Extensions:
server/lib/
directoryserver/venv/
pip-tools
, poetry
, or pipenv
to create reproducible bundlesPYTHONPATH
to include bundled packages via mcp_config.env
Node.js Extensions:
npm install --production
to create node_modules
node_modules
directory with your extensionnpm ci
or yarn install --frozen-lockfile
for reproducible buildsserver.entry_point
Binary Extensions:
No configuration available
Related projects feature coming soon
Will recommend related projects based on sub-categories