mcp

This MCP server lets AppsAI projects connect to external AI tooling such as Claude Code, Claude Desktop, Cursor, Windsurf, and other AI tools through the AppsAI MCP ecosystem. By wiring the server with your AppsAI API key, agents and humans can access the connected toolchain to build and deploy full-stack apps, manage projects, and leverage AI-assisted development workflows. Typical use includes provisioning the server in Claude Code or Cursor/Windsurf configurations so agents can invoke capabilities like project management, code generation, and backend/frontend orchestration from within AppsAI projects.

To use it, configure the MCP server in your development environment (via Claude Code, Claude Desktop, or Cursor/Windsurf) with the provided command and environment variables. The server exposes tools that agents can call through the AppsAI platform, enabling workflows such as creating projects, deploying frontends, managing databases, and deploying infrastructure, all mediated by AI prompts and built-in MCP resources. Ensure your APPSAI_API_KEY is securely supplied to authorize tool access for your account and projects.

Prerequisites:

• Node.js (with npm) installed on your machine, or access to an environment that can run npx.
• An APPSAI_API_KEY for authenticating with AppsAI services.

Installation steps:

1. Obtain your API key from AppsAI (Settings > Billing > API Keys).
2. Install Node.js if not already installed. Example (macOS/Linux):

# using a package manager
# macOS (Homebrew)
brew install node
# Linux (apt)
sudo apt-get update
sudo apt-get install -y nodejs npm

3. Run the MCP server via npx with your API key. Example:

APPSAI_API_KEY=your_key npx -y @appsai/mcp-server

4. If you prefer Claude Code integration, add via Claude Code using the example command:

claude mcp add appsai -e APPSAI_API_KEY=your_key -- npx -y @appsai/mcp-server

5. For Claude Desktop configuration, add to claude_desktop_config.json (example shown in README):

{
  "mcpServers": {
    "appsai": {
      "command": "npx",
      "args": ["-y", "@appsai/mcp-server"],
      "env": {
        "APPSAI_API_KEY": "your_key"
      }
    }
  }
}

6. For Cursor/Windsurf, configure with the command and environment variables as documented in the README. Ensure the server is reachable from your AppsAI project and that the API key is kept secure.

Tips and notes:

• Keep your APPSAI_API_KEY secure; avoid committing it to version control.
• The npm package name for this MCP server is @appsai/mcp-server; using npx ensures you grab the latest release if you omit a local install.
• You can configure multiple MCP servers in AppsAI projects by naming them (e.g., appsai) and attaching different environment keys as needed.
• If you need to change the server label or command, adjust the mcp_config accordingly and redeploy the AppsAI project settings.
• Review API usage and quotas in your AppsAI account to anticipate costs or limits when invoking external tools.
• For debugging, verify that APPSAI_API_KEY is correct and that the environment where the MCP server runs can access the AppsAI backend endpoints.