About raycast
raycast is an MCP server for automating Raycast workflows through AI assistants. Its tools cover extensions, workflows, search, and system actions, as well as authentication, clipboard, and shortcut controls.
Key features
- 01Manage Raycast extensions and publishing
- 02Create and run workflows
- 03Search and launch apps, files, or commands
- 04Manage clipboard history
- 05Trigger shortcuts and control windows
Use cases
- 01Create and run workflows through an AI assistant
- 02Find and launch local apps or commands
- 03Manage extensions and related authentication
- 04Automate tasks with shortcuts and clipboard actions
MCP support
The MCP server exposes Raycast tools to MCP clients for authentication, extensions, workflows, search, clipboard, shortcuts, window behavior, and system actions.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMERaycast MCP Server
A comprehensive Model Context Protocol (MCP) server for Raycast workflow automation, providing 9 powerful tools to integrate Raycast with AI assistants like Claude.
Features
🔧 9 Comprehensive Tools
- raycast_auth - Manage Raycast and service authentication
- raycast_extensions - Manage Raycast extensions and store integration
- raycast_workflows - Create and manage Raycast workflows and automations
- raycast_search - Search and launch applications, files, or commands via Raycast
- raycast_clipboard - Manage clipboard history via Raycast
- raycast_shortcut - Trigger Raycast shortcuts and hotkeys
- raycast_window - Control Raycast window behavior
- raycast_system - Access system functions through Raycast
- Plus additional workflow tools
🚀 Capabilities
- Full OAuth integration support for multiple services
- Extension management and publishing workflow
- Custom workflow creation and execution
- System automation and control
- Clipboard management
- Search and navigation
Installation
Via Claude Desktop
Add to your claude_desktop_config.json:
{
"mcpServers": {
"raycast": {
"command": "node",
"args": ["/path/to/raycast-mcp/dist/index.js"],
"env": {
"RAYCAST_API_KEY": "${RAYCAST_API_KEY}",
"RAYCAST_TEAM_ID": "${RAYCAST_TEAM_ID}"
}
}
}
}
Via NPX (Coming Soon)
npx raycast-mcp-server
Via Smithery
smithery install raycast-mcp-server
Development
Prerequisites
- Node.js 18+
- TypeScript
- Raycast installed on macOS
Setup
git clone https://github.com/ExpertVagabond/raycast-mcp-server.git
cd raycast-mcp-server
npm install
npm run build
Running Locally
npm start
Building for Production
npm run build
Usage Examples
Authentication Management
# Setup GitHub authentication
{"tool": "raycast_auth", "arguments": {"action": "setup", "service": "github"}}
# Validate credentials
{"tool": "raycast_auth", "arguments": {"action": "validate", "service": "github"}}
Extension Management
# Search for extensions
{"tool": "raycast_extensions", "arguments": {"action": "search", "query": "github"}}
# List installed extensions
{"tool": "raycast_extensions", "arguments": {"action": "list"}}
Workflow Automation
# Create a custom workflow
{"tool": "raycast_workflows", "arguments": {
"action": "create",
"name": "morning-routine",
"steps": [
{"type": "command", "action": "open-calendar"},
{"type": "api_call", "action": "fetch-weather"},
{"type": "notification", "action": "daily-summary"}
]
}}
# Execute a workflow
{"tool": "raycast_workflows", "arguments": {"action": "execute", "name": "morning-routine"}}
Environment Variables
RAYCAST_API_KEY- Raycast API key (if available)RAYCAST_TEAM_ID- Raycast team ID (if applicable)
Contributing
- Fork the repository
- Create a feature branch
- Make your changes
- Add tests if applicable
- Submit a pull request
License
MIT
Support
For issues and feature requests, please use the GitHub Issues page.
Built with ❤️ for the Raycast and MCP communities.
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.