Databutton

by databutton

13 stars
15.6k downloads
Not rated
GitHub Website

About

Enables planning and scaffolding of business applications with React frontends and Python backends, helping developers establish structured foundations for Databutton-powered projects.

Details

Author
databutton
Repository
databutton/databutton-mcp
GitHub stars
13
Downloads
15,593
License
MIT License
Categories
Developer Tools, AI, Project Management, Automation, Design, Frontend, Infrastructure

- Initial app planning and starting point creation
- Works with Databutton’s AI agent
- Supports React and Python APIs/MCPs
- Includes a planning mode for generating an initial plan
- Built and run locally via npm

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Databutton
    Command (node, npx, python, etc.) /path/to/databutton/build/index.js

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

To use with Claude Desktop, add the server config:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "databutton": {
      "command": "/path/to/databutton/build/index.js"
    }
  }
}

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "databutton": {
            "cwd": null,
            "env": {},
            "args": [],
            "shell": false,
            "command": "/path/to/databutton/build/index.js"
        }
    }
}

Linux

{
    "cwd": null,
    "env": [],
    "args": [],
    "shell": false,
    "command": "/path/to/databutton/build/index.js"
}

Macos

{
    "cwd": null,
    "env": [],
    "args": [],
    "shell": false,
    "command": "/path/to/databutton/build/index.js"
}

Windows

{
    "cwd": null,
    "env": [],
    "args": [],
    "shell": false,
    "command": "/path/to/databutton/build/index.js"
}

We released a game changing way for anyone to build their own MCP servers in Databutton. Learn more athttps://www.databutton.com/mcp

Databutton's (https://www.databutton.com/) AI agent builds and deploys frontends and backends in React and Python APIs/MCPs, for building beautiful business apps with unbounded complexity.

The agent has a planning mode for generating an initial plan for your app.

This MCP server is for doing doing initial app planning and creating a good starting point for an app.

To use with Claude Desktop, add the server config:

On MacOS:~/Library/Application Support/Claude/claude_desktop_config.jsonOn Windows:%APPDATA%/Claude/claude_desktop_config.json

{ "mcpServers": { "databutton": { "command": "/path/to/databutton/build/index.js" } } }

Since MCP servers communicate over stdio, debugging can be challenging. We recommend using theMCP Inspector, which is available as a package script:

The Inspector will provide a URL to access debugging tools in your browser.

This is a web browser that enables your coding agent, such as Claude Code, to visit websites on your behalf and assist you in identifying bugs or creating UI test cases.

An AI-powered server that facilitates feature discussions between developers and AI, acting as a lead developer to guide implementation and architectural decisions.

A conversation-driven development framework for rapid MVP and POC creation.

Agent-native developer Q&A API with MCP + A2A endpoints for citations, job pickup, and answer submission.

MCP bridge that lets Claude Code delegate heavy tasks to the Antigravity CLI (agy) — purpose-built tools, model routing with fallback, session continuity, and output truncation to save Claude's context and tokens.

Assists AI developers with requirement clarification, module design, and technical architecture.

Embeds intelligent guidance into AI workflows to organize development and ensure quality.

Open-source AI coding stack — bundled MCP servers, agent runtime, and developer tooling for shipping AI-native dev tools.

Local agent workbench bundling OpenHands, Goose, Aider, and ashlrcode against one local LLM, with ashlr-plugin MCP servers pre-wired.

Async Parallel Antigravity for Codex & Claude Code

Run parallel, resumable, human-operable Antigravity CLI sessions from Codex, Claude Code, or any MCP-capable agent harness.

knowledge network for AI coding agents. Developers connect their agents to a shared pool of verified solutions — saving tokens, reducing debugging time, and getting better results. Solution authors earn when their work helps others.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.