Vibe Gate MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 107 installs a week from npm. Last commit 7 Oct 2026.
Adversarial Quality Gate MCP for vibe-coding: IDE AI vs Critic AI, human decides on deadlock
We read the source, 15 h ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
const child = spawn(target.command, target.args, {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add vibe-gate-mcp -- npx -y vibe-gate-mcp
{
"mcpServers": {
"vibe-gate-mcp": {
"command": "npx",
"args": [
"-y",
"vibe-gate-mcp"
]
}
}
}
[mcp_servers.vibe-gate-mcp]
command = "npx"
args = ["-y", "vibe-gate-mcp"]
{
"mcpServers": {
"vibe-gate-mcp": {
"command": "npx",
"args": [
"-y",
"vibe-gate-mcp"
]
}
}
}
{
"servers": {
"vibe-gate-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"vibe-gate-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
VIBE_WORKSPACE_ROOT (Consumer project root (auto-detected from the working directory if omitted)), CRITIC_PROVIDER (Critic provider: openai, anthropic, google, minimax, opencode, codex-cli, claude-code, cursor-agent or opencode-cli (a signed-in local CLI is auto-detected if omitted)), CRITIC_MODEL (Model id override; required for opencode-cli as provider/model), CRITIC_PERSONA (Critic persona: security-first, performance-freak or clean-code-monk), OPENAI_API_KEY (OpenAI API key (CRITIC_PROVIDER=openai)), ANTHROPIC_API_KEY (Anthropic API key (CRITIC_PROVIDER=anthropic)), GOOGLE_GENERATIVE_AI_API_KEY (Google Gemini API key (CRITIC_PROVIDER=google)), MINIMAX_API_KEY (MiniMax API key (CRITIC_PROVIDER=minimax)), OPENCODE_API_KEY (OpenCode API key (CRITIC_PROVIDER=opencode)), OPENCODE_PLAN (OpenCode plan: go (subscription) or zen (pay-as-you-go)), CODEX_CLI_PATH (Path to the codex executable (CRITIC_PROVIDER=codex-cli)), CLAUDE_CODE_CLI_PATH (Path to the claude executable (CRITIC_PROVIDER=claude-code)), CURSOR_AGENT_CLI_PATH (Path to the agent executable (CRITIC_PROVIDER=cursor-agent)), OPENCODE_CLI_PATH (Path to the opencode executable (CRITIC_PROVIDER=opencode-cli)), CRITIC_CLI_TIMEOUT_MS (Local CLI timeout in milliseconds, from 1000 to 600000), DEBUG (Log parse and read failures to stderr).
Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
Quality verification for AI agents and MCP servers. 6-axis scoring, adversarial probes.
Human-in-the-loop approval gateway for AI agents over MCP: request, decide, approve.
Mechanical write gates, evidence receipts, and adversarial review for AI coding agents.
Patent-pending semantic memory for AI agents: quality-gated writes, conflict tracking. Free trial.
Work-queue kernel for AI coding agents: dependencies, worktree isolation, quality gates, recovery
Structural code-quality tools for AI coding agents.
Local code-quality rules, findings, preview-first safe fixes and gate results for coding agents.
Answers built from our own checks of this server.