coco — security grade SAFE, quality 62/100

Security audit verdict: SAFE · quality 62/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by coco-research · MCP Server · ★ 413

Last updated: 2026-10-03 · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is coco safe to install? View the security audit →

About coco

CoCo Super Intelligence Summon an advisory board of 495 world-class minds — right inside your AI coding session. CoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an entire engineering department: routed expert panels that deliberate and decide, then 226 skills, 386 commands, and disk-persistent state that ship what they decided. Open-core (MIT core · proprietary Super Intelligence) · installs in 90 seconds · 100% local · no telemetry [![CI](https://img.shields.io/github/actions/workflow/status/coco-research/co

agent-skills agents-md ai ai-agents claude-code codex cursor developer-tools llm-tools mcp

Quick Facts

Stars	413
Forks	12
Language	HTML
Category	MCP Server
Quality Score	62.3262241381669/100
Open Issues	73
Last Updated	2026-10-03
Created	2026-04-25
Platforms	claude-code, codex, mcp
Est. Tokens	~26k

Compatible Skills

These tools work well together with coco for enhanced workflows:

agentic-os — semantic(0.27)+complementary+same_lang+similar_pop+shared_platform (59%)
C.R.I.S.P — semantic(0.26)+complementary+same_lang+similar_pop+shared_platform (59%)

coco alternative? Top 6 similar tools

Looking for a coco alternative? If you're comparing coco 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.

ok-skills by mxyhi · ⭐ 492
Curated AI coding agent skills and AGENTS.md playbooks for Codex, Claude Code, Cursor, OpenClaw, and other SKI
agent-skills by jdrhyne · ⭐ 241
A collection of AI agent skills for Clawdbot, Claude Code, Codex
ai-devkit by codeaholicguy · ⭐ 1.6k
The control plane for AI coding agents.
claude-workflow-v2 by CloudAI-X · ⭐ 1.4k
Universal Claude Code workflow plugin with agents, skills, hooks, and commands
quint-code by m0n0x41d · ⭐ 1.3k
Engineering decisions engine that know when they're stale. Frame, compare, decide — with evidence decay and p
agent-deck by asheshgoplani · ⭐ 995
Terminal session manager for AI coding agents. One TUI for Claude, Gemini, OpenCode, Codex, and more.

More MCP Server Tools

Explore other popular mcp server tools:

n8n ⭐ 206.6k
gemini-cli ⭐ 107.2k
awesome-mcp-servers ⭐ 95.6k
TrendRadar ⭐ 62.2k
context7 ⭐ 62.6k
UI-TARS-desktop ⭐ 39.1k
chrome-devtools-mcp ⭐ 52.9k
github-mcp-server ⭐ 33.3k
gpt-researcher ⭐ 29.9k
Scrapling ⭐ 85.4k

View all MCP Server tools →

Popular HTML Agent Tools

douyin-mcp-server ⭐ 1.2k · MCP Server
N8N2MCP ⭐ 132 · MCP Server
mcp-memory ⭐ 158 · MCP Server
XActions ⭐ 559 · MCP Server
superdesign-mcp-claude-code ⭐ 77 · MCP Server

Frequently Asked Questions

What is coco?

coco is CoCo Super Intelligence is the orchestration layer that turns Claude Code, Cursor, or Codex into an engineering department: a routed advisory board, 226 skills, 386 commands, persistent state. Local. . It is categorized as a MCP Server with 413 GitHub stars.

What programming language is coco written in?

coco is primarily written in HTML. It covers topics such as agent-skills, agents-md, ai.

How do I install or use coco?

You can find installation instructions and usage details in the coco GitHub repository at github.com/coco-research/coco. The project has 413 stars and 12 forks, indicating an active community.

What are the best alternatives to coco?

The top alternatives to coco on Agent Skills Hub include ok-skills, agent-skills, ai-devkit. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. 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:

View on GitHub → Browse MCP Server tools