Cloud desktops for AI agents: create a Linux computer, see its screen, click, type and run tasks.
Run one of the commands below, then pick your client in the next section.
npm
npx -y mandala-computer-mcpStreamable HTTP
https://app.mandala.computer/mcp
Pick your client — the config below is generated for this server (both local and hosted-endpoint forms).
claude_desktop_config.json
{
"mcpServers": {
"mcp-mandalacomputer": {
"command": "npx",
"args": [
"-y",
"mandala-computer-mcp"
],
"env": {
"MANDALA_API_KEY": "<YOUR_MANDALA_API_KEY>",
"MANDALA_MODEL_KEY": "<YOUR_MANDALA_MODEL_KEY>"
}
}
}
}Remote (hosted) endpoint
https://app.mandala.computer/mcp
Claude Desktop: Settings → Connectors → Add custom connector, paste this URL.
Format verified against the official Claude Desktop docs ↗.
terminal
claude mcp add --env MANDALA_API_KEY=<YOUR_MANDALA_API_KEY> --env MANDALA_MODEL_KEY=<YOUR_MANDALA_MODEL_KEY> mcp-mandalacomputer -- npx -y mandala-computer-mcp
terminal
claude mcp add --transport http mcp-mandalacomputer https://app.mandala.computer/mcp
Format verified against the official Claude Code docs ↗.
.cursor/mcp.json
{
"mcpServers": {
"mcp-mandalacomputer": {
"command": "npx",
"args": [
"-y",
"mandala-computer-mcp"
],
"env": {
"MANDALA_API_KEY": "<YOUR_MANDALA_API_KEY>",
"MANDALA_MODEL_KEY": "<YOUR_MANDALA_MODEL_KEY>"
}
}
}
}.cursor/mcp.json (hosted endpoint)
{
"mcpServers": {
"mcp-mandalacomputer": {
"url": "https://app.mandala.computer/mcp"
}
}
}Format verified against the official Cursor docs ↗.
.vscode/mcp.json
{
"servers": {
"mcp-mandalacomputer": {
"command": "npx",
"args": [
"-y",
"mandala-computer-mcp"
],
"env": {
"MANDALA_API_KEY": "<YOUR_MANDALA_API_KEY>",
"MANDALA_MODEL_KEY": "<YOUR_MANDALA_MODEL_KEY>"
}
}
}
}.vscode/mcp.json (hosted endpoint)
{
"servers": {
"mcp-mandalacomputer": {
"type": "http",
"url": "https://app.mandala.computer/mcp"
}
}
}Format verified against the official VS Code docs ↗.
mcp_config.json
{
"mcpServers": {
"mcp-mandalacomputer": {
"command": "npx",
"args": [
"-y",
"mandala-computer-mcp"
],
"env": {
"MANDALA_API_KEY": "<YOUR_MANDALA_API_KEY>",
"MANDALA_MODEL_KEY": "<YOUR_MANDALA_MODEL_KEY>"
}
}
}
}mcp_config.json (hosted endpoint)
{
"mcpServers": {
"mcp-mandalacomputer": {
"serverUrl": "https://app.mandala.computer/mcp"
}
}
}Format verified against the official Windsurf docs ↗.
Defined in the server's official registry manifest. Required secrets are shown as <YOUR_…> placeholders in the configs above.
MANDALA_API_KEY secret — API key from Settings → API keys. Optional after `mandala login`, which saves one.MANDALA_MODEL_KEY secret — Your model provider key. Optional; turns on run_agent.Distributed as npm, Streamable HTTP, listed under Developer Tools. Review our MCP security guide before granting access to real data.
Run the install command shown above, then paste the config for your client (Claude Desktop, Claude Code, Cursor, VS Code or Windsurf) into its MCP settings and restart the client.
The MCP server itself is free to install. The source is public on https://github.com/mandalacomputer/mcp. Any third-party service it calls may require its own API key and account.
Any MCP-compatible client can use it, including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf and custom agents.
Publish this server? Link back with a badge on your README or site — copy either snippet.
Markdown
[](https://mcpnav.net/server/mcp-mandalacomputer/)
HTML
<a href="https://mcpnav.net/server/mcp-mandalacomputer/"><img src="https://mcpnav.net/badge/mcp-mandalacomputer.svg" alt="Listed on MCPNav" height="20"></a>