vibe-check-mcp-server MCP — Use Cases, Install & Live Demo

Name: vibe-check-mcp-server MCP Server
Author: PV-Bhat

Why use it

Key features

vibe_check tool interrupts with pushback before irreversible actions
vibe_learn captures per-session lessons for in-context improvement
Constitution tools define per-session rules the agent must follow
Pure prompt-wrapping — no data leaves your chosen LLM provider

Live Demo

What it looks like in practice

vibe-check.replay ▶ ready

0/0

Install

Pick your client

~/Library/Application Support/Claude/claude_desktop_config.json · Windows: %APPDATA%\Claude\claude_desktop_config.json

{
  "mcpServers": {
    "vibe-check": {
      "command": "npx",
      "args": [
        "-y",
        "vibe-check-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Open Claude Desktop → Settings → Developer → Edit Config. Restart after saving.

~/.cursor/mcp.json · .cursor/mcp.json

{
  "mcpServers": {
    "vibe-check": {
      "command": "npx",
      "args": [
        "-y",
        "vibe-check-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Cursor uses the same mcpServers schema as Claude Desktop. Project config wins over global.

VS Code → Cline → MCP Servers → Edit

{
  "mcpServers": {
    "vibe-check": {
      "command": "npx",
      "args": [
        "-y",
        "vibe-check-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Click the MCP Servers icon in the Cline sidebar, then "Edit Configuration".

~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "vibe-check": {
      "command": "npx",
      "args": [
        "-y",
        "vibe-check-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Same shape as Claude Desktop. Restart Windsurf to pick up changes.

~/.continue/config.json

{
  "mcpServers": [
    {
      "name": "vibe-check",
      "command": "npx",
      "args": [
        "-y",
        "vibe-check-mcp-server"
      ]
    }
  ]
}

Continue uses an array of server objects rather than a map.

~/.config/zed/settings.json

{
  "context_servers": {
    "vibe-check": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "vibe-check-mcp-server"
        ]
      }
    }
  }
}

Add to context_servers. Zed hot-reloads on save.

claude mcp add vibe-check -- npx -y vibe-check-mcp-server

One-liner. Verify with claude mcp list. Remove with claude mcp remove.

Use Cases

Real-world ways to use vibe-check-mcp-server

Sanity-check a plan before a destructive action with vibe-check

👤 Anyone running agents with write access ⏱ ~10 min beginner

When to use: The agent is about to delete files, run a migration, or deploy — you want a second opinion.

Flow

Invoke vibe_check on the plan

Before running the migration, call vibe_check on this plan: [paste]. What could go wrong?✓ Copied

→ Pushback list: unchecked assumptions, missing rollback, scope creep
Resolve or ignore each concern explicitly

Address each concern — either mitigate or explicitly dismiss as out of scope.✓ Copied

→ Annotated plan ready to run

Outcome: Fewer 'oh no' moments after destructive actions.

Pitfalls

Agent dismisses all concerns rubber-stamp style — Require the agent to restate each concern and the specific mitigation

Combine with: sequentialthinking-tools

Enforce session rules with vibe-check's constitution

👤 Teams sharing agent workflows ⏱ ~10 min intermediate

When to use: You want certain rules (never push to main, always write tests first) enforced across a session.

Flow

Set the constitution

Use update_constitution to set these rules for this session: [list]. Enforce via CPI on every tool call that could violate them.✓ Copied

→ Rules acknowledged; subsequent violations get interrupted
Inspect when in doubt

Call check_constitution to see what's currently in effect.✓ Copied

→ Current rules list

Outcome: Consistent agent behavior within a session without repeating rules every message.

Capture lessons from agent mistakes with vibe_learn

👤 Agent developers iterating on prompts ⏱ ~5 min beginner

When to use: The agent made a classic mistake; you want it not to repeat.

Flow

Log the lesson

Call vibe_learn with: mistake='deleted prod table without snapshot', lesson='always take a snapshot before DDL on prod'.✓ Copied

→ Lesson stored for the session
Rely on it later

(later in same session) Attempt a DDL — vibe_check surfaces the stored lesson✓ Copied

→ Interrupt with the relevant past lesson

Outcome: In-session memory of 'don't do that again' without prompt engineering.

Combinations

Pair with other MCPs for X10 leverage

vibe-check + sequentialthinking-tools

Plan + pushback loop

Plan with sequentialthinking_tools, then call vibe_check on the plan before executing step 1.✓ Copied

vibe-check + overture

Visual plan + vibe-check layer

After Overture produces the plan graph, run vibe_check on it and surface concerns as annotations.✓ Copied

Tools

What this MCP exposes

Tool	Inputs	When to call	Cost
vibe_check	plan: str, context?: str	Before any non-trivial or irreversible action	1 LLM call via your configured provider
vibe_learn	mistake: str, lesson: str	Immediately after a mistake, while fresh	0
update_constitution	rules: str[]	Session start or policy change	0
check_constitution		Debug unexpected interrupts	0
reset_constitution		Start fresh	0

Cost & Limits

What this costs to run

API quota: Uses your chosen LLM's quota
Tokens per call: 500-3000 for vibe_check
Monetary: LLM token cost only
Tip: Only vibe_check on substantive plans — skipping it on trivial edits saves tokens

Security

Permissions, secrets, blast radius

Credential storage: LLM API key in env (OPENAI_API_KEY, ANTHROPIC_API_KEY, etc.)

Data egress: Only to your configured LLM provider

Troubleshooting

Common errors and fixes

vibe_check returns empty concerns

Plan input was too vague — include concrete steps and side effects

Agent ignores vibe_check output

Make the system prompt require addressing each concern before proceeding

npx cannot find @pv-bhat/vibe-check-mcp

The published scope is @pv-bhat; pin latest explicitly: npx -y @pv-bhat/vibe-check-mcp@latest

Alternatives

vibe-check-mcp-server vs others

Alternative	When to use it instead	Tradeoff
sequentialthinking-tools	You want planning, not pushback	Different shape — no adversarial second model
overture	You want visual gating instead of text pushback	Heavier setup

More

Resources

📖 Read the official README on GitHub

🐙 Browse open issues

🔍 Browse all 400+ MCP servers and Skills