mcpField
G
Greta

Greta

Remote
greta.shDeveloper Tools0Updated 1w ago
RepositoryVisit website

About Greta

Greta is a remote MCP server for building, deploying, and growing hosted websites and full-stack apps through an AI agent. It also supports starting from marketplace templates and tracking project activity and costs.

Key features

  1. 01Build full-stack apps and websites
  2. 02Start from marketplace templates
  3. 03Deploy backends and publish websites
  4. 04Run capped website growth loops
  5. 05Check projects, credits, and site status

Use cases

  1. 01Create a hosted app through an AI agent
  2. 02Publish a website at a live URL
  3. 03Review suggested growth pages and publish holds

MCP support

Greta provides a remote MCP server over Streamable HTTP, authenticated with OAuth 2.1. MCP clients connect agents to Greta’s app-building, deployment, publishing, and site-management capabilities.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.greta.sh
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

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 README

Greta MCP server

Connect your AI agent to Greta, the AI app builder. Ask Claude, ChatGPT, Cursor or any MCP client to build you a website or an app, and Greta makes a real hosted project with a live URL, not a mockup.

This is a remote MCP server. There is nothing to install or run.

https://mcp.greta.sh

Transport: Streamable HTTP. Auth: OAuth 2.1 (your client opens a browser and you sign in to Greta).

Connect

Claude Code

claude mcp add greta --transport http https://mcp.greta.sh

Then run /mcp, pick greta and sign in.

Claude.ai, ChatGPT, Cursor, VS Code and other MCP clients: add a custom connector or server with the URL above; the client signs you in to Greta.

What your agent can do

  • Build a full-stack app (frontend, backend, database) or a self-growing website by chatting with Greta's builder, and follow each build
  • Start from a template: search Greta's marketplace of finished apps and make one your own
  • Deploy an app's backend and publish a website to its live address
  • Grow a website: run its nightly growth loop with a credit cap, see what it suggests to be cited by AI answer engines, queue pages, review what the publish gate held, and read what each night ran and cost
  • Check projects, credits and how a site is doing

Building, deploying and growth runs use Greta credits. Every paid action states its cost, and the agent can cap what a call may spend.

Links

Comments

Markdown supported

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.