agents-shipgate — security grade SAFE, quality 68/100

Security audit verdict: SAFE · quality 68/100

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 ThreeMoonsLab · MCP Server · ★ 89

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

🔒 Is agents-shipgate safe to install? View the security audit →

About agents-shipgate

Agents Shipgate Your coding agent changed what your AI agent can do — Agents Shipgate shows you what changed before it merges. The deterministic merge gate for AI-generated agent capability changes. Local-first and static by default — no agent execution, tool calls, LLM calls, or network access. Agents Shipgate is an open-source CLI and GitHub Action for local-first, static Tool-Use Readiness review. It scans MCP, OpenAPI, OpenAI Agents SDK, Anthropic Messages API, Google ADK, LangChain/LangGraph, CrewAI,

agent-governanceagent-release-readinessai-agent-securityai-agentsci-cdcrewaigithub-actionsgoogle-adklangchainmcp

Quick Facts

Stars89
Forks3
LanguagePython
CategoryMCP Server
LicenseApache-2.0
Quality Score67.7961373807449/100
Open Issues113
Last Updated2026-09-23
Created2026-04-25
Platformscli, mcp, python
Est. Tokens~20k

agents-shipgate alternative? Top 6 similar tools

Looking for a agents-shipgate alternative? If you're comparing agents-shipgate 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.

  • faramesh-core by faramesh · ⭐ 100

    Governance-as-Code for AI agents. Declarative constraints with deterministic enforcement. Provisioning Identit

  • DashClaw by ucsandman · ⭐ 306

    Remote approvals, policy checks, and execution evidence for unattended AI agents.

  • oreilly-ai-agents by sinanuozdemir · ⭐ 299

    An introduction to the world of AI Agents

  • node9-proxy by node9-ai · ⭐ 216

    IAM for your AI agents. Set what Claude Code, Codex, Gemini, Cursor and any MCP server are allowed to do, revi

  • martin-loop by Keesan12 · ⭐ 190

    Make AI coding agents safe to scale autonomously: assign work, cap spend, enforce policy, verify output, roll

  • mcp by taskade · ⭐ 164

    🤖 Taskade MCP · Official MCP server and OpenAPI to MCP codegen. Build AI agent tools from any OpenAPI API and

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Python Agent Tools

Frequently Asked Questions

What is agents-shipgate?

agents-shipgate is The deterministic merge gate for AI-generated agent capability changes — a local-first, static Tool-Use Readiness review for MCP, OpenAPI, and SDK tool surfaces. Open-source CLI + GitHub Action.. It is categorized as a MCP Server with 89 GitHub stars.

What programming language is agents-shipgate written in?

agents-shipgate is primarily written in Python. It covers topics such as agent-governance, agent-release-readiness, ai-agent-security.

How do I install or use agents-shipgate?

You can find installation instructions and usage details in the agents-shipgate GitHub repository at github.com/ThreeMoonsLab/agents-shipgate. The project has 89 stars and 3 forks, indicating an active community.

What license does agents-shipgate use?

agents-shipgate 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 agents-shipgate?

The top alternatives to agents-shipgate on Agent Skills Hub include faramesh-core, DashClaw, oreilly-ai-agents. 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