OpenTag — 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 linxidnju · MCP Server · ★ 567

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

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

About OpenTag

OpenTag Open-source, channel-native multiplayer AI gateway with shared, auditable team knowledge. Tag local AI agents into Slack threads, with local execution, visible progress, approvals, audit trails, and pluggable agent runtimes. English · 简体中文 · User Guide · Security · Contributing OpenTag brings AI agents into the place where team work already happens: Slack channels and threads. Instead of running an agent from one person's terminal and pasting results back into chat, a team can mention , discuss the task in the same thread, approve risky actions when needed, and keep the outcome visible to everyone who has access to that channel. ✨ What You Can Do Ask an agent to investigate a bug from a Slack thread. Let teammates add context before or

agent-gatewayai-agentsautomationclaudeclaude-codeclaude-tagcodexdeveloper-toolsmcpnodejs

Quick Facts

Stars567
Forks0
LanguageJavaScript
CategoryMCP Server
Quality Score61.832162028052/100
Last Updated2026-07-10
Created2026-06-27
Platformsclaude-code, cli, codex, docker, mcp, node
Est. Tokens~14k

Compatible Skills

These tools work well together with OpenTag for enhanced workflows:

  • my-claude-devteam — semantic(0.21)+complementary+same_lang+similar_pop+shared_platform (57%)
  • clay — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)
  • gpt-team-register — semantic(0.20)+complementary+same_lang+similar_pop+shared_platform (57%)

OpenTag alternative? Top 6 similar tools

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

  • OpenContext by 0xranx · ⭐ 729

    A personal context store for AI agents and assistants—reuse your existing coding agent CLI (Codex/Claude/OpenC

  • Overture by SixHq · ⭐ 630

    Overture is an open-source, locally running web interface delivered as an MCP (Model Context Protocol) server

  • sandboxed.sh by Th0rgal · ⭐ 513

    Safe runtime for autonomous on-chain AI agents: isolated sandboxes, Library skills, encrypted secrets.

  • deepcontext-mcp by Wildcard-Official · ⭐ 275

    DeepContext is an MCP server that adds symbol-aware semantic search to Claude Code, Codex CLI, and other agent

  • meridian by markmdev · ⭐ 181

    Zero-config Claude Code setup with enforced task scaffolding, structured memory, persistent context after comp

  • claude-code-plugins-plus-skills by jeremylongshore · ⭐ 2.7k

    471 plugins, 3,069 skills, 347 agents for Claude Code. Open-source marketplace at tonsofskills.com with the cc

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular JavaScript Agent Tools

Frequently Asked Questions

What is OpenTag?

OpenTag is Open-source, channel-native agent gateway for Slack. Route team threads to Claude Code, Codex, OpenCode, Docker, HTTP agents, and custom CLIs with policy, approvals, memory, audit logs, and artifacts.. It is categorized as a MCP Server with 567 GitHub stars.

What programming language is OpenTag written in?

OpenTag is primarily written in JavaScript. It covers topics such as agent-gateway, ai-agents, automation.

How do I install or use OpenTag?

You can find installation instructions and usage details in the OpenTag GitHub repository at github.com/linxidnju/OpenTag. The project has 567 stars and 0 forks, indicating an active community.

What are the best alternatives to OpenTag?

The top alternatives to OpenTag on Agent Skills Hub include OpenContext, Overture, sandboxed.sh. 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