Log inSubmit server
Vibe Check MCP Server logo

Vibe Check MCP Server

by PV-Bhat

Adds LLM-based oversight that helps agents catch misalignment, avoid scope creep, and pause before risky actions.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Vibe Check MCP Server

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "pv-bhat-vibe-check-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "@pv-bhat/vibe-check-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

We couldn’t confirm it starts correctly

We ran the install command but it didn't respond within our test window — this can mean a slow first-time install rather than a real problem.

npx -y @pv-bhat/vibe-check-mcp

No response to initialize.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 1mo ago.

Overview

PV-Bhat/vibe-check-mcp-server MCP server adds a second-LLM review layer that helps an agent reassess plans, assumptions, uncertainty, and risk. It uses Chain-Pattern Interrupts to pause reasoning when risk increases, then provides metacognitive feedback before the main agent continues. The package runs through npm with either STDIO or streamable HTTP transport and supports Gemini, Claude, GPT, and OpenRouter providers. Reach for it when agents tend to over-engineer tasks, lose alignment, or take irreversible actions without a sanity check.

Use cases

  • Review plans before irreversible agent actions
  • Interrupt over-engineered implementation paths
  • Maintain alignment across multi-step sessions
  • Record mistakes and fixes for later reflection

Key features

  • Second-LLM metacognitive feedback
  • Adaptive Chain-Pattern Interrupts
  • Risk and uncertainty signals
  • Session history summaries
  • Optional vibe_learn records
  • STDIO and HTTP transports

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 1d ago

Recent health check succeeded.

19/20 checks healthy over the last 78d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 8d ago via OSV.dev · @pv-bhat/vibe-check-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars502Stargazers on the source repository.
npm downloads316Package downloads in the last 30 days.
Last commit6d agoMost recent push to the default branch.
Install checkInconclusiveDidn't respond in our test window — often a slow first install.
Directory activity7 viewsConfig copies, upvotes, and views on AllMCPs.

How Vibe Check MCP Server works

What PV-Bhat/vibe-check-mcp-server MCP server does

PV-Bhat/vibe-check-mcp-server MCP server provides an oversight layer for AI agents. It is designed to interrupt flawed or overcomplicated plans before they continue, especially when the agent is drifting from the user's goal or approaching an irreversible action. The server asks a second large language model for metacognitive feedback rather than directly replacing the primary agent's reasoning.

The project focuses on two related problems: pattern inertia, where an agent continues a familiar approach despite warning signs, and reasoning lock-in, where a confident but flawed plan becomes difficult to change. Its feedback can include traits, uncertainty, and risk scores that help determine whether the agent should pause and reconsider.

How it works

An agent can call the Vibe Check functionality during a task, with system-prompt guidance recommending checks before irreversible operations. Chain-Pattern Interrupts provide phase-aware prompts that challenge assumptions. A separate intervention policy can consume the resulting signals and decide when the main agent should be interrupted before resuming work.

When a session ID is supplied, the server can summarize earlier advice to maintain continuity. The optional vibe_learn capability records mistakes and fixes for later reflection.

Setup and configuration

The documented quick-start path requires Node.js 20 or newer and the published npm package. For an MCP client using standard input/output, run:

Terminal
npx -y @pv-bhat/vibe-check-mcp start --stdio

The same command can be added to an MCP client configuration with npx as the command and -y, @pv-bhat/vibe-check-mcp, start, and --stdio as arguments. The README specifically names Claude Desktop, Cursor, and Windsurf as compatible clients.

For local HTTP inspection, start the server with --http --port 2091. The health endpoint is /healthz, and JSON-RPC requests use /mcp.

Tools and capabilities

PV-Bhat/vibe-check-mcp-server MCP server supports:

  • Metacognitive feedback from a second LLM.
  • Adaptive, phase-aware Chain-Pattern Interrupts.
  • Risk, uncertainty, and trait signals for oversight.
  • Session history summaries when sessionId is provided.
  • Optional learning records through vibe_learn.
  • STDIO and streamable HTTP transports.

Limitations and notes

The project is in maintenance mode. Community forks and contributions are permitted under the MIT license.

The server depends on a second LLM for its review layer, so provider availability and configuration are relevant to deployment. Its documented role is advisory oversight: it supplies interruption and reflection signals rather than guaranteeing that an agent will never make an unsafe or misaligned decision.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Vibe Check MCP Server

Run `npx -y @pv-bhat/vibe-check-mcp start --stdio` with Node.js 20 or newer, then add the same command and arguments to an MCP client configuration.

Yes.

It provides second-LLM feedback about agent alignment, assumptions, uncertainty, traits, and risk, with interruptions intended to prevent reasoning lock-in and scope creep.

Yes. The documented command starts HTTP transport on port 2091, with `/healthz` for health checks and `/mcp` for JSON-RPC requests.

No. The project is in maintenance mode, with active feature development ended and future work limited to maintenance, security, and bug fixes.

Related MCP servers

All in Other Tools and Integrations All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewVibe Check MCP Server AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/pv-bhat-vibe-check-mcp-server?style=directory)](https://allmcps.com/mcp/pv-bhat-vibe-check-mcp-server)
HTML Embed
<a href="https://allmcps.com/mcp/pv-bhat-vibe-check-mcp-server"><img src="https://allmcps.com/api/badge/pv-bhat-vibe-check-mcp-server?style=directory" alt="Vibe Check MCP Server on AllMCPs" /></a>