Getting Started

This guide walks you through the three steps to start using HeadlessOps with your AI tools (Claude Desktop, Cursor, Roo Code, and others). No API key required to get started.

Step 1 — Create an Account & Workspace

Sign up at app.headlessops.ai. During signup you will create your first Workspace — an isolated environment that holds your integrations, credentials, data stores, and team members.

Once signed in you will land on your workspace dashboard. From here you can manage everything: integrations, runs, credentials, and your team.

Already have an account? Use the workspace switcher at the top of the dashboard to create an additional workspace (e.g. a staging environment or a separate client workspace).

Step 2 — Invite Your Team

Collaboration is built in. Invite colleagues to your workspace so they can co-develop automations, review runs, and manage credentials together.

1. Go to Workspace Settings → Members
2. Click Invite Member
3. Enter your colleague's email address and select their role:
   • DEVELOPER — can create, update, and deploy integrations
   • ADMIN — same as DEVELOPER plus invite management and API key creation
   • VIEWER — read-only access to integrations and run logs
4. Click Send Invite

The invited user receives an email with a link to accept. They log in (or create an account) and are immediately added to the workspace.

See Users & RBAC for the full role reference and permission matrix.

Step 3 — Connect Your AI Tool via MCP

HeadlessOps exposes a native Model Context Protocol (MCP) server that lets AI agents interact with the platform directly — reading, writing, deploying, and running integrations without leaving your IDE.

The MCP server URL is:

https://app.headlessops.ai/mcp

Authentication uses OAuth 2.1 with PKCE — your AI client will open a browser window on first connection and ask you to log in and grant the requested scopes. No API key needed.

Connect Claude Desktop

Edit your Claude Desktop config file:

• macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• Windows: %APPDATA%\Claude\claude_desktop_config.json

Add the HeadlessOps MCP server:

{
  "mcpServers": {
    "headlessops": {
      "url": "https://app.headlessops.ai/mcp",
      "type": "http"
    }
  }
}

Restart Claude Desktop. On next launch, Claude will prompt you to authorize the connection in your browser.

Connect Cursor

Open Cursor settings and navigate to Features → Model Context Protocol. Add a new MCP server:

{
  "name": "HeadlessOps",
  "url": "https://app.headlessops.ai/mcp",
  "type": "http"
}

Save and restart Cursor. On first use, you will be redirected to authorize the connection.

Connect Roo Code

Open .roo/mcp.json (or the global MCP settings panel) in VS Code and add:

{
  "headlessops": {
    "url": "https://app.headlessops.ai/mcp",
    "type": "http"
  }
}

For full setup details, local proxy configuration, and example agent prompts, see Connect Claude Desktop and Connect Cursor & Roo Code.

You're Ready

Once your AI client is connected, you can start giving it natural language instructions like:

• "Create a webhook integration that logs incoming payloads and saves them to a data store"
• "Write a scheduled integration that runs every Monday at 9am and sends a Slack summary"
• "List all integrations in my workspace and show me the last 5 runs"

Your AI agent handles the scripting — you focus on what you want to automate.

Next Steps

• MCP Setup Overview — understand OAuth scopes, workspace resolution, and available tools
• Platform Guide — learn about workspaces, roles, and resource isolation
• Scripting Guide — write and customize your own integration.yaml files
• Examples — real-world automation patterns to get inspired

Need API access for CI/CD or scripts? API keys are covered in Workspace Management → API Key Management.