mosoo-agent-driver — security grade SAFE, quality 72/100

Security audit verdict: SAFE · quality 72/100

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 langgenius · MCP Server · ★ 73

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

🔒 Is mosoo-agent-driver safe to install? View the security audit →

About mosoo-agent-driver

agent-driver One Driver Kernel. Every agent backend. The runtime that drives a sandbox-hosted agent session inside Mosoo. is the standalone runtime driver for sandbox-hosted agent sessions. It runs inside the sandbox and drives a single agent session from boot to stop. The core produc

acpagent-client-protocolagent-driveragent-harnessagent-protocolagent-runtimebunclaude-agent-sdkcodexcoding-agent

Quick Facts

Stars73
Forks11
LanguageTypeScript
CategoryMCP Server
LicenseApache-2.0
Quality Score71.7678635591703/100
Open Issues15
Last Updated2026-09-18
Created2026-06-05
Platformsclaude-code, cli, codex, mcp, node
Est. Tokens~16k

Compatible Skills

These tools work well together with mosoo-agent-driver for enhanced workflows:

  • open-managed-agents — semantic(0.45)+complementary+rare_topics+same_lang+similar_pop+shared_platform (70%)
  • codex-collab — semantic(0.18)+complementary+shared_fw(anthropic)+same_lang+similar_pop+shared_platform (64%)
  • agentrove — semantic(0.25)+complementary+rare_topics+same_lang+similar_pop+shared_platform (63%)
  • platform — semantic(0.21)+complementary+rare_topics+same_lang+similar_pop+shared_platform (62%)

mosoo-agent-driver alternative? Top 6 similar tools

Looking for a mosoo-agent-driver alternative? If you're comparing mosoo-agent-driver 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.

  • bitrouter by bitrouter · ⭐ 233

    The minimal interpretable model router that learns & adapts to your agent workflows

  • lightcode by SDSLeon · ⭐ 66

    One window for all your AI coding agents. Run Claude, Codex, OpenCode, Gemini, Antigravity, Cursor, and Copilo

  • agentrove by Mng-dev-ai · ⭐ 332

    Self-hosted AI coding workspace to run and orchestrate Claude Code, Codex, Copilot, Cursor, Grok and OpenCode

  • golembot by 0xranx · ⭐ 322

    Any Agent × Any Provider × Anywhere. Connect Cursor, Claude Code, OpenCode, or Codex to Slack, Telegram, Disco

  • maestro by ReinaMacCredy · ⭐ 232

    Local-first coordination for human and agent work: durable work, decisions, dispatches, evidence, and prompt-f

  • palot by ItsWendell · ⭐ 190

    Just another desktop client for OpenCode 2. Manage projects, sessions, parallel agents, requests, and changes

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular TypeScript Agent Tools

Frequently Asked Questions

What is mosoo-agent-driver?

mosoo-agent-driver is Runtime-neutral AI execution bridge for Claude Agent SDK, Codex app-server, and Agent Client Protocol (ACP).. It is categorized as a MCP Server with 73 GitHub stars.

What programming language is mosoo-agent-driver written in?

mosoo-agent-driver is primarily written in TypeScript. It covers topics such as acp, agent-client-protocol, agent-driver.

How do I install or use mosoo-agent-driver?

You can find installation instructions and usage details in the mosoo-agent-driver GitHub repository at github.com/langgenius/mosoo-agent-driver. The project has 73 stars and 11 forks, indicating an active community.

What license does mosoo-agent-driver use?

mosoo-agent-driver is released under the Apache-2.0 license, making it free to use and modify according to the license terms.

What are the best alternatives to mosoo-agent-driver?

The top alternatives to mosoo-agent-driver on Agent Skills Hub include bitrouter, lightcode, agentrove. 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