A security MCP server for coding assistants, offering rules and tools for reviewing applications built with listed web frameworks, databases, payment systems, and AI libraries. MCP is a standard way for an assistant to call external tools.

Use it for security-oriented review of projects using technologies such as Next.js, Supabase, Stripe, Prisma, GraphQL, or the listed AI and web tools.

It gives a coding assistant security checks tailored to the technologies in an AI-generated application. The description does not specify the individual checks or their results.

GuardVibe — Plugin for Gemini CLI by goklab

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

Clone the repo

git clone --depth 1 https://github.com/goklab/guardvibe

Made for: Gemini CLI.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/plugins/goklab/guardvibe/gemini-extension/github.svg)](https://agentmods.dev/plugins/goklab/guardvibe/gemini-extension)

Your own site

<a href="https://agentmods.dev/plugins/goklab/guardvibe/gemini-extension"><img src="https://agentmods.dev/badge/plugins/goklab/guardvibe/gemini-extension/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/plugins/goklab/guardvibe/gemini-extension"><img src="https://agentmods.dev/badge/plugins/goklab/guardvibe/gemini-extension.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session not measured What this adds to a session before it is invoked.

When invoked not measured Not applicable: nothing here is loaded into a session.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Security

Grade A, and why

GuardVibe scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured today.

The scan reads gemini-extension.json. This mod also ships 2 executable files (scripts/intel-check.mjs, scripts/release-gate.mjs), listed below but not scanned — reading those needs a real analyzer, not pattern matching.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

gemini-extension.json · 13 lines

What it actually says

{
  "name": "GuardVibe",
  "version": "3.59.0",
  "description": "Security MCP for vibe coding. 594 rules, 39 tools for Next.js, Supabase, Clerk, Stripe, Prisma, tRPC, Hono, GraphQL, Convex, Turso, Uploadthing, AI SDK, and the full AI-generated stack.",
  "mcpServers": {
    "guardvibe": {
      "command": "npx",
      "args": ["-y", "guardvibe"]
    }
  },
  "contextFileName": "GEMINI.md"
}

Files

What ships with it

2 files beside gemini-extension.json in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

today Changed 1d5dc37ee10e
yesterday Changed 9110e573b2de
2d ago Changed 72ac65b2921c
3d ago Changed f97fa6193e7b
4d ago Changed a2e97fe58d5c
5d ago Changed 29cd56116020
6d ago Changed 7450497bf388
7d ago Changed e01d056a7e40
10d ago Changed 9c6df5c74e95
12d ago First seen · 13 lines scan A 09d7622311fb

Subscribe to this mod's changes

GuardVibe is a plugin published in the GitHub repository goklab/guardvibe (6 stars, last pushed yesterday), licensed Apache-2.0. Its token cost is not measured: this kind of file is read by the harness, not the model. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-22.

Security ai-security claude clerk cursor mcp nextjs

ai-app-security

Security guardrails for AI-built apps: OWASP/API/LLM/MCP rules applied while building, an /audit skill for full reviews, and a hook that blocks secret commits.

xChechi/xche-ai-app-security-pack · not measured

kernora-agent-security

Grounds your AI coding agent in a cited security baseline (OWASP/CWE/EU AI Act) and warns before risky actions. Advisory, free, read-only. Real-time blocking is Kernora Axiora.

kernora-ai/agent-sec · not measured

before-you-build

Pre-build product risk review for founders, product teams, and AI-assisted builders before implementation starts.

wshobson/agents · not measured

mc-agent-toolkit

Monte Carlo Agent Toolkit — data observability skills and enforcement hooks for AI coding agents.

monte-carlo-data/mc-agent-toolkit · not measured

kage

Kage manages your memory and agents. It briefs and runs agents in isolated git worktrees for a single run or a multi-wave goal, re-runs the checks itself instead of trusting the agent's report, and remembers what it learns so each brief is smarter than the last.

kage-core/Kage · not measured

mosaic-bridge

Mosaic Bridge — Unity MCP assistant agents for scene building, shader creation, and session continuity.

MosaicXR-AI/mosaic-bridge · not measured