About Automo Build
Automo Build is an AI app builder for creating, testing, reviewing, and publishing React, TypeScript, and Supabase applications from plain-language descriptions. Its remote MCP server lets AI tools operate projects, builds, specialist agents, and deployments.
Key features
- 01Create and manage projects
- 02Prompt the app builder
- 03Consult CTO, Doctor, Security, and QA agents
- 04Publish applications
- 05Use core or read-only tool catalogs
Use cases
- 01Create an application from a plain-language brief
- 02Ask specialist agents to review a build
- 03Operate projects and deployments through an AI tool
MCP support
Provides remote Streamable HTTP access for MCP clients, with OAuth sign-in on first use. Separate endpoints offer core operator, read-only, and builder-subagent routing options.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://mcp.automo.build/mcp{profile}claude mcp add --transport http build-automo-automo-build https://mcp.automo.build/mcp{profile}{"mcpServers":{"build-automo-automo-build":{"type":"http","url":"https://mcp.automo.build/mcp{profile}"}}}Open in Cursor{"servers":{"build-automo-automo-build":{"type":"http","url":"https://mcp.automo.build/mcp{profile}"}}}Open in VS Code{"mcpServers":{"build-automo-automo-build":{"type":"http","url":"https://mcp.automo.build/mcp{profile}"}}}{"mcpServers":{"build-automo-automo-build":{"serverUrl":"https://mcp.automo.build/mcp{profile}"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEAutomo Build MCP server
Automo Build is an AI app builder. Describe software in plain language and get a real React, TypeScript and Supabase application, tested, reviewed and deployed to a public URL. This server lets your AI tool operate it as you: create projects, prompt the builder, ask the CTO, Doctor, Security and QA agents, and publish.
It is free to start: a trial, then a USD 0 Free plan with a monthly credit allowance, the built-in backend and web publishing.
Connect
The server is remote, so there is nothing to install or run. It speaks Streamable HTTP at:
https://mcp.automo.build/mcp
Sign-in is OAuth in the browser on first use. There is no API key and no client registration; tokens are scoped and revocable.
| Client | How |
|---|---|
| Claude Code | /plugin marketplace add Desygner/automo-build-mcp then /plugin install automo-build |
| Claude.ai | Settings, Connectors, Add custom connector, https://mcp.automo.build/mcp |
| Cursor | Install the Automo Build plugin, or npx automo-build connect cursor |
| Codex | npx automo-build connect codex |
| Cline | Add the server below to cline_mcp_settings.json |
| Any MCP client | Add https://mcp.automo.build/mcp as a remote Streamable HTTP server |
{
"mcpServers": {
"automo-build": {
"type": "streamableHttp",
"url": "https://mcp.automo.build/mcp"
}
}
}
Narrower catalogs live at /mcp/core (the core operator set) and /mcp/observe (read-only). Append /builders to route build instructions through builder subagents.
Links
- Developer portal: https://automo.build/developers
- For agents: AGENTS.md and https://automo.build/llms.txt
- Agent registration: https://automo.build/auth.md
- OpenAPI: https://mcp.automo.build/openapi.json
- Server card: https://mcp.automo.build/.well-known/mcp-server-card.json
- Privacy policy: https://automo.build/privacy-policy
- Support: [email protected]
What is in this repository
server.json: the official MCP Registry entry.plugins/claude-code: the Claude plugin (Claude Code and Cowork), with the operator skill, first-run setup and/automo-handoff.plugins/cursor: the Cursor plugin, with the same server and skill.plugins/openai: the ChatGPT and Codex plugin.npm-cli:npx automo-build connect.
Everything here is generated from the Automo Build runtime; edits made directly in this repository are overwritten.
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.