Imagine. Build. Ship.
If you can imagine it, OBTO can build it. Sign up, connect your AI client, and deploy your first application through conversation.
Sign Up
Go to obto.co and click Sign in in the top-right corner. Authenticate with your Google account. Your OBTO instance is created automatically — no setup required.
Copy Your MCP Endpoint
After signing in, you'll see your personal MCP server URL on the landing page. This URL is unique to your account and connects your AI client to your OBTO instance.
Copy this URL. You'll need it in Step 4.
💡 Your MCP endpoint is the bridge between your AI chat interface and the OBTO deployment engine. Every app you build through conversation gets deployed through this connection.
Get the OBTO Skill
The OBTO Skill(obto-developer) is a file called SKILL.md that teaches your AI model how to build and deploy applications on OBTO. Download it from GitHub:
👉 github.com/obto-inc/platform
| Client | Where to put SKILL.md |
|---|---|
| Claude Desktop | Add to project knowledge or attach as a file |
| Claude Web | Upload as a file attachment in your conversation |
| Cursor | Place in workspace root or .cursor/skills/ |
| VS Code | Place in workspace root directory |
| AntiGravity | Place in .agent/skills/ directory |
Connect to Your AI Client
Select your client. Replace YOUR_MCP_ENDPOINT with the URL from Step 2.
Claude.ai — Web Interface
The simplest option. Native remote MCP via Connectors.
Settings → Connectors (claude.ai/settings/connectors)
Click "Add custom connector"
Paste your OBTO MCP endpoint URL
Click "Add" — transport auto-detected
In chat: "+" → "Connectors" to toggle on
Free: 1 connector. Pro/Max/Team/Enterprise: unlimited. Team/Enterprise orgs add via Org settings → Connectors first.
Claude Desktop App
Uses Connectors UI for remote servers — not the config file.
Recommended: Connectors UI
"+" at bottom of chat → "Connectors" → "Manage Connectors"
Add custom connector with your endpoint URL
Syncs across Claude.ai, Desktop, and Mobile
Alternative: Config file with mcp-remote
Requires Node.js. Bridges stdio to HTTP.
{
"mcpServers": {
"obto": {
"command": "npx",
"args": [
"mcp-remote",
"https://<my obto.co host>.obto.co/ms/mcp"
]
}
}
}The config file does not support a direct "url" field. {"url":"https://..."} silently fails. Use Connectors UI or mcp-remote. Fully quit & restart after changes.
Claude Code (CLI)
Native HTTP support — simplest CLI setup.
One-command setup
claude mcp add --transport http obto-mcp https://<my obto.co host>.obto.co/ms/mcpWith scope
# User scope (all projects) claude mcp add --transport http --scope user obto-mcp https://<my obto.co host>.obto.co/ms/mcp # Project scope (team via .mcp.json) claude mcp add --transport http --scope project obto-mcp https://<my obto.co host>.obto.co/ms/mcp
All flags must come before the server name. claude mcp add obto-mcp --transport http fails.
Config file
~/.claude.json (user) or .mcp.json (project root):
{
"mcpServers": {
"obto-mcp": {
"type": "http",
"url": "https://<my obto.co host>.obto.co/ms/mcp"
}
}
}Useful: claude mcp list · claude mcp get obto-mcp · /mcp · claude --mcp-debug
VS Code with GitHub Copilot (Agent Mode)
Built-in since VS Code 1.99+. Requires Copilot extension + chat.agent.enabled: true.
Option A — Workspace (recommended)
Create .vscode/mcp.json:
{
"servers": {
"obto": {
"type": "http",
"url": "https://<my obto.co host>.obto.co/ms/mcp"
}
}
}Option B — User settings.json
{
"mcp": {
"servers": {
"obto": {
"type": "http",
"url": "https://<my obto.co host>.obto.co/ms/mcp"
}
}
}
}VS Code uses "servers" — not "mcpServers". #1 config error. Verify: Copilot Chat → Agent mode → tools icon.
VS Code with Continue.dev
YAML config. Tools only in Agent mode.
mcpServers: - name: OBTO type: streamable-http url: https://<my obto.co host>.obto.co/ms/mcp
If streamable-http fails, try sse. Continue uses kebab-case: sse, stdio, streamable-http.
VS Code with Cline
Access: MCP Servers icon → Configure → Configure MCP Servers
{
"mcpServers": {
"obto": {
"url": "https://<my obto.co host>.obto.co/ms/mcp",
"type": "sse",
"disabled": false,
"timeout": 60
}
}
}Start with "sse" — more reliable than "streamableHttp" (Cline uses camelCase). Green dot = connected.
VS Code with Roo Code
Access: 🔌 MCP icon → Edit Global/Project MCP
{
"mcpServers": {
"obto": {
"type": "sse",
"url": "https://<my obto.co host>.obto.co/ms/mcp",
"disabled": false,
"timeout": 60
}
}
}type is required — omitting it errors. Kebab-case: "sse", "streamable-http", "stdio".
Cursor IDE
Native remote MCP. Simplest IDE config.
{
"mcpServers": {
"obto": {
"url": "https://<my obto.co host>.obto.co/ms/mcp"
}
}
}Auto-detects transport. No "type" needed. Green indicator in Settings → Tools & MCP.
Cursor caps at ~40 tools across all servers. Toggle off/on or restart if tools don't appear.
Windsurf IDE (Codeium)
Own config path, different key name for URL.
{
"mcpServers": {
"obto": {
"serverUrl": "https://<my obto.co host>.obto.co/ms/mcp"
}
}
}"serverUrl" not "url". Most common Windsurf MCP error.
JetBrains IDEs
All IntelliJ-based IDEs since 2025.1.
Settings → Tools → AI Assistant → Model Context Protocol (MCP)
+ Add → HTTP type
Paste config, OK → Apply
{
"mcpServers": {
"obto": {
"url": "https://<my obto.co host>.obto.co/ms/mcp"
}
}
}"Import from Claude" button imports existing Claude Desktop configs.
Zed Editor
Stdio only — needs mcp-remote (Node.js required).
{
"context_servers": {
"obto": {
"source": "custom",
"command": "npx",
"args": ["-y", "mcp-remote", "https://<my obto.co host>.obto.co/ms/mcp"],
"env": {}
}
}
}"source": "custom" is required or Zed silently skips the server.
Amazon Q Developer
Native HTTP. Config: ~/.aws/amazonq/default.json or .amazonq/default.json:
{
"mcpServers": {
"obto": {
"type": "http",
"url": "https://<my obto.co host>.obto.co/ms/mcp"
}
}
}Universal Fallback (Any stdio-only Client)
mcp-remote bridges stdio to HTTP. Wrap in whatever root key your client expects:
{
"command": "npx",
"args": ["-y", "mcp-remote", "https://<my obto.co host>.obto.co/ms/mcp"]
}Build
You're connected. Select the obto-developer skill and then just describe what you want:
The AI reads the OBTO Skill, writes the backend logic, creates the frontend, deploys everything in the correct order, and your app goes live at yourapp.obto.co.