Overview
App Settings control Workshop’s platform-level behavior and integrations. Unlike Agent Settings which affect how the AI behaves during conversations, App Settings configure the underlying system capabilities and external connections. Access App Settings through the main Settings menu (gear icon). These settings apply across all projects and conversations.Secrets management
Secrets are sensitive values like API keys, database passwords, or access tokens that your applications need to interact with external services. Workshop provides a built-in system to store and use them securely.How secrets work
- Secure storage: Workshop uses your operating system’s native keychain (macOS Keychain, Windows Credential Manager, Linux Secret Service) to store secret values. Raw values are never stored in Workshop’s own files.
- Local access: Secrets remain on your machine and are only accessed when needed by processes Workshop initiates on your behalf.
- Key tracking: Workshop maintains a list of secret names you’ve stored, but actual values are encrypted and managed by your system’s secure storage.
Managing secrets
Add a secret
Enter a descriptive key name (e.g.,
OPENAI_API_KEY, DATABASE_PASSWORD), enter the value, and click Add Secret.Updating and deleting secrets
- Update: Click the edit icon next to any secret, enter the new value, and click Update.
- Delete: Remove secrets you no longer need from the Secrets tab.
Security details
- Case insensitive: Workshop finds secrets regardless of case —
OPENAI_API_KEY,openai_api_key, andOpenAI_API_Keyall work. - Permission prompts: The first time Workshop accesses a secret, your OS may ask for permission. You can allow once, allow always, or deny.
- No exposure: Secret values are never displayed in conversation logs or technical outputs — only referenced by their key names.
If you have secrets from an older Workshop format, you’ll see a migration banner in the Secrets tab. Click Migrate Secrets to convert them to the current secure system.
MCP (Model Context Protocol) support
The Model Context Protocol is a standard for connecting AI models to tools, data sources, and services. Workshop supports both using and building MCP servers.Using MCP servers
MCP extends Workshop’s capabilities like an infinitely expanding toolset. Enable servers to give Workshop access to databases, deployment platforms, documentation, browser automation, and more. Managing MCP servers:- Go to Settings (gear icon) and select the MCP tab
- Browse three sections:
| Section | Description |
|---|---|
| Configured Servers | View, enable/disable, and manage your installed MCP servers |
| Server Directory | Browse and install curated, Workshop-tested servers (Neon, Netlify, GitHub, Context7, and more) |
| Add Custom Server | Install any MCP server from the broader ecosystem via GitHub URL or local path |
Using MCP in conversations
Workshop integrates with enabled MCP servers naturally — often requiring no special instructions:Building MCP servers
Workshop can build MCP servers from natural language descriptions, test them, and add them to your available tools — all in a single conversation:MCP best practices
- Only enable servers you’re actively using to reduce context overhead
- Test new servers in non-critical projects first
- Use secure credential storage (Secrets) for server authentication
- Disable unused tools within servers to keep context focused
Control Center
The Control Center provides quick-action buttons for common development tasks, accessible from within your project. It helps both non-technical builders and experienced developers speed through routine operations.Version control setup
Set up Git for your project with a single click:- Initializes a Git repository with appropriate
.gitignore - Makes an initial commit with current project state
- Provides Commit Changes for subsequent saves
Workshop often initializes version control and commits changes on its own during development. The Control Center buttons let you trigger these actions at specific moments.
Application management
Start, stop, and monitor your applications directly from the Control Center:- Start Application — Workshop analyzes your project structure and creates a custom startup script
- Stop Application — Safely terminates running processes
- View Application — Opens your running app in the browser
- View Logs / Restart / Attach to Chat — Debug and manage running applications
Documentation generation
Generate or improve project documentation with one click:- Generate Documentation — Creates a comprehensive
README.mdfrom your project structure - Improve README — Enhances existing documentation with current project state
Interactive Terminal
Workshop can handle command-line tools that require interactive input — something most AI agents cannot do. The Interactive Terminal enables Workshop to:- Create and manage interactive terminal sessions
- Answer prompts from CLI tools (scaffolding wizards, interactive installers, deployment setup)
- Handle long-running processes like development servers
create-vite or create-next-app), deployment wizards, and interactive configuration tools — resulting in faster development from tested, standard boilerplate.
Terminal sessions are visible in the Control Center, showing session type, duration, and status.