Sugar runs on your own machine — the client starts it, so there is no endpoint to ping. 295 installs a week from pypi. Last commit 16 Sep 2026.
Autonomous AI development system with persistent task queue and background execution
We read the source, 20 h ago · rules 3dff92dd89df
A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.
result = subprocess.run(
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const proc = spawn(command, args, {
result = subprocess.run(
shell=True,
self._log_file_path = os.path.join(log_dir, f"{self.task_id}.md")
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add sugar -- uvx sugarai
{
"mcpServers": {
"sugar": {
"args": [
"sugarai"
],
"command": "uvx"
}
}
}
[mcp_servers.sugar]
command = "uvx"
args = ["sugarai"]
{
"mcpServers": {
"sugar": {
"args": [
"sugarai"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"sugar": {
"args": [
"sugarai"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
ANTHROPIC_API_KEY (Anthropic API key for Claude model access), GITHUB_TOKEN (GitHub token for repository access), SUGAR_DEFAULT_REPO (Default repository in owner/repo format).
The author declared them in the registry entry; get the values from the project itself.
AI-powered Kanban TUI for autonomous development workflows with agent orchestration
Persistent memory, task coordination, and HITL queue for AI coding sessions.
Autonomous MCP server and background agent for managing live event logistics.
Memori MCP server — persistent AI memory with recall and augmentation tools
Persistent task board synced across Claude Code and Claude.ai, backed by Supabase.
Deterministic pre-execution safety certification for autonomous AI agents.
Deterministic execution authorization for AI agents and automated systems.
Bounded agent exploration with persistent progress, deterministic receipts, and return contracts.
Answers built from our own checks of this server.