awesome-dxt
🚀 A curated list of awesome Desktop Extensions (DXT) and MCP servers for Claude Desktop. Discover, share, and contribute to the growing ecosystem of AI-powered local tools and automations.
claude mcp add --transport stdio mcpstar-awesome-dxt-mcp node path/to/server.js \ --env DESCRIPTION="Placeholder for Awesome DXT MCP server runtime (adjust path to actual server entry if available)"
How to use
Awesome DXT MCP appears to be a curated MCP server catalog intended for Claude Desktop ecosystems. It aggregates Desktop Extensions (DXT) and MCP servers, enabling users to discover, install, and manage local AI-powered tools. If you run this MCP server, you can expect to expose a directory of extension manifests or server descriptors that Claude Desktop can query to fetch available MCP servers, their capabilities, and any required configuration. Typical usage would involve starting the MCP server and using the client tooling to browse extensions, install a chosen server, and then invoke the MCP endpoints or tools provided by individual servers. The tooling ecosystem referenced in the repository includes the DXT CLI (for packaging and validating DXT extensions) and the MCP SDKs for Node.js and Python, which you would use when developing or integrating new MCP servers or extensions.
How to install
Prerequisites:
- Node.js (recommended) or a compatible runtime for your MCP server implementation
- Access to the project source or a running copy of the Awesome DXT MCP server
Step-by-step:
- Install Node.js from https://nodejs.org/ and verify with node -v and npm -v
- Obtain the Awesome DXT MCP server code (clone or download the repository)
- Navigate to the project directory
- Install dependencies (if a package.json exists): npm install
- Start the MCP server (adjust command as needed for your setup): node path/to/server.js
- If the server requires environment configuration, create an .env file or export the needed variables prior to startup. Example placeholders: export MCP_SERVER_PORT=3000 export MCP_SERVER_HOST=localhost
If you are using Docker, build and run the container following your project’s Dockerfile and docker-compose setup (if provided). If no Docker configuration exists, refer to the Node.js startup above.
Additional notes
Notes and tips:
- This entry appears to be a directory/listing for Awesome Desktop Extensions (DXT) MCP servers rather than a single executable server. If you intend to run a local instance, confirm the actual entry point (server.js or equivalent) and provide the correct path in the mcp_config.
- Ensure Claude Desktop or the MCP client tooling can reach the host and port where the MCP server is exposed (consider firewall and network settings).
- When developing extensions, you can leverage the MCP SDKs (Node.js or Python) for creating, packaging, and validating MCP servers or extensions.
- If you plan to publish or share this as a DXT package, ensure manifests and dependencies are bundled according to the DXT specification referenced in the documentation section of the repository.
Related MCP Servers
bytebot
Bytebot is a self-hosted AI desktop agent that automates computer tasks through natural language commands, operating within a containerized Linux desktop environment.
awesome-agent-skills
A curated list of skills, tools, tutorials, and capabilities for AI coding agents (Claude, Codex, Antigravity, Copilot, VS Code)
toolsdk -registry
MCPSDK.dev(ToolSDK.ai)'s Awesome MCP Servers and Packages Registry and Database with Structured JSON configurations. Supports OAuth2.1, DCR...
awesome-claude-dxt
Awesome Claude Desktop Extensions (dxt) (not only Claude) mcpb
mcp-mail
📧 MCP Mail Tool - AI-powered email management tool | 基于 MCP 的智能邮件管理工具
fast-filesystem
A high-performance Model Context Protocol (MCP) server that provides secure filesystem access for Claude and other AI assistants.