by roboticforce · MCP Server · ★ 98
Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h
pipx install sugarai
claude mcp add sugar -- sugar mcp memory
Taken from the project's README on GitHub. Check the security audit before running it.
None of the 42 rules matched — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against 42 published rules built on the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →
The quality score combines nine heuristic checks of the repo and its README: completeness, clarity, specificity, examples, structure, agent readiness, step-by-step content, instruction quality and security notes. It rates how well the project explains itself to an agent, not the code.
| Stars | 98 |
| Forks | 16 |
| Language | Python |
| Category | MCP Server |
| Quality Score | 74/100 |
| Open Issues | 4 |
| Last Updated | 2026-10-14 |
| Created | 2025-08-21 |
| Platforms | claude-code, mcp, python |
| Est. Tokens | ~16k |
Sugar Autonomous issue resolution for AI-assisted development. Security scanners find vulnerabilities. Dependabot opens issues. Copilot flags problems. Sugar reads the issue, writes the fix, runs the tests, and opens the PR.
These tools work well together with sugar for enhanced workflows:
Looking for a sugar alternative? If you're comparing sugar with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.
Outcome-based persistent memory MCP server for Claude Code and OpenCode. Good advice promoted, bad advice demo
Local-first persistent agentic memory powered by Recursive Memory Harness (RMH). Open source must win.
Persistent memory for AI coding agents
Server-enforced workflow discipline for AI agents. An MCP server providing persistent work items, dependency g
MCP server that lets Claude Code and other AI agents read and search large PDFs, one file or a whole folder: a
Biologically-inspired persistent memory engine for Claude Code. 26 cognitive subsystems, Hopfield networks, pr
Explore other popular mcp server tools:
Grades come from a rule-based scan built on the SlowMist agent-security taxonomy: 42 published rules, covering credential harvesting, data exfiltration, curl | sh installers and more. It is a first-layer scan, not a manual audit — we say so rather than overstate it.
The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.
Sources & who's responsible: