AICre8 MCP Server
# @aicre8/mcp-server
MCP server for [AICre8](https://aicre8.dev) — connect AI agents to create, edit, and deploy web projects.
Works with **Claude Desktop**, **Cursor**, **Claude Code**, and any MCP-compatible client.
## Setup
### 1. Get an API Key
Go to [aicre8.dev/settings](https://aicre8.dev/settings) and create an API key in the API Keys section.
### 2. Configure Your Client
#### Claude Desktop
Edit `~/Library/Application Support/Claude/claude_desktop_config.json` (Mac) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows):
```json
{
"mcpServers": {
"aicre8": {
"command": "npx",
"args": ["@aicre8/mcp-server"],
"env": {
"AICRE8_API_KEY": "ak_live_your_key_here"
}
}
}
}
```
#### Cursor
Add to `.cursor/mcp.json` in your project or global config:
```json
{
"mcpServers": {
"aicre8": {
"command": "npx",
"args": ["@aicre8/mcp-server"],
"env": {
"AICRE8_API_KEY": "ak_live_your_key_here"
}
}
}
}
```
#### Claude Code
```bash
claude mcp add aicre8 -- npx @aicre8/mcp-server
```
Set `AICRE8_API_KEY` in your environment.
### 3. Start Using
Once configured, ask your AI agent things like:
- "List my AICre8 projects"
- "Create a new project called Coffee Shop"
- "Build a landing page with a dark theme and hero section"
- "Deploy the project"
## Available Tools
| Tool | Description |
|------|-------------|
| `list_projects` | List all your projects |
| `create_project` | Create a new project |
| `generate_code` | Generate or modify code with AI |
| `read_file` | Read a file from the project sandbox |
| `write_file` | Write a file to the project sandbox |
| `run_command` | Run a shell command in the sandbox |
| `deploy_project` | Deploy to a live branded URL |
## Environment Variables
| Variable | Required | Default | Description |
|----------|----------|---------|-------------|
| `AICRE8_API_KEY` | Yes | — | Your API key (starts with `ak_live_`) |
| `AICRE8_API_URL` | No | `https://aicre8.dev/api/v1` | API base URL |
## API Documentation
Full REST API docs: [aicre8.dev/developers](https://aicre8.dev/developers)
## License
MIT
TDQS
Scored across 7 tools
Each tool has a clearly distinct purpose with no overlap: create_project, deploy_project, generate_code, list_projects, read_file, run_command, and write_file all target specific actions in the AICre8 project lifecycle. An agent can easily distinguish between them, such as separating file operations (read_file, write_file) from project management (create_project, list_projects) and execution (run_command, generate_code).
All tool names follow a consistent verb_noun pattern with snake_case, such as create_project, deploy_project, generate_code, list_projects, read_file, run_command, and write_file. This uniformity makes the tool set predictable and easy to navigate, with no deviations in style or convention.
With 7 tools, the server is well-scoped for managing AICre8 projects, covering creation, deployment, code generation, listing, and file/sandbox operations. Each tool earns its place by addressing a core aspect of the workflow, avoiding bloat while ensuring comprehensive functionality for the domain.
The tool set provides strong coverage for AICre8 project management, including CRUD-like operations (create, list, deploy) and sandbox interactions (read/write files, run commands, generate code). A minor gap exists in the lack of update or delete operations for projects, but agents can work around this by managing files or regenerating code as needed.