What environment variables are required?
`BULT_API_URL` (set to `https://app.bult.ai`) and `BULT_API_TOKEN` (your Bult.ai API token) must be set.
@bultcloud
Basic information
Deploy and manage Bult.ai cloud hosting projects from MCP clients like Cursor, Claude Desktop, and Claude Code. Create projects and services, deploy GitHub repositories or Docker images, manage routes and volumes, inspect logs, and troubleshoot deployments from your AI assistant.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"bult": {
"command": "npx",
"args": [
"-y",
"@bultcloud/mcp-server"
],
"env": {
"BULT_API_URL": "https://app.bult.ai",
"BULT_API_TOKEN": "your_bult_api_token"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Bult.ai MCP Server lets MCP clients deploy and manage Bult.ai cloud hosting resources directly from an AI assistant. It is designed for developers and teams who want to control their cloud infrastructure through conversational AI tools.
Install by adding a JSON configuration to your MCP client settings, using npx -y @bultcloud/mcp-server as the command and setting the environment variables BULT_API_URL and BULT_API_TOKEN.
`BULT_API_URL` (set to `https://app.bult.ai`) and `BULT_API_TOKEN` (your Bult.ai API token) must be set.
Add a JSON entry to your `mcpServers` configuration with `"command": "npx"`, `"args": ["-y", "@bultcloud/mcp-server"]`, and the required environment variables.
It can create and manage projects, deploy GitHub repos and Docker images, create services and public routes, manage volumes, and view logs to

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.


Read Everframe bug reports, crashes and tickets from your AI agent: annotated screenshots, console logs, network requests, breadcrumbs, stack traces and device context from web, iOS, Android and TV apps. Eight read-only

ArtiBot Cloud MCP (Zhijiangyun 智匠云) — cloud MCP server for robot manipulation data & GPU workloads. 15 tools: robot fleet management, data collection & video recording, post-processing pipelines, and benchmark evaluation
Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app
Comments