/ Annuaire / Playground / vibe-check-mcp-server
● Communauté PV-Bhat ⚡ Instantané

vibe-check-mcp-server

par PV-Bhat · PV-Bhat/vibe-check-mcp-server

A second LLM that challenges your agent's plan before execution — catches tunnel vision, over-engineering, reasoning lock-in.

vibe-check-mcp (PV-Bhat) provides metacognitive feedback to agents via Chain-Pattern Interrupts (CPI). Invokes a second model to push back on assumptions at key decision points. Project is in maintenance mode (v2.8.0 final) but still fully functional under MIT.

Pourquoi l'utiliser

Fonctionnalités clés

Démo en direct

Aperçu en pratique

vibe-check.replay ▶ prêt
0/0

Installer

Choisissez votre 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
    }
  }
}

Ouvrez Claude Desktop → Settings → Developer → Edit Config. Redémarrez après avoir enregistré.

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "vibe-check": {
      "command": "npx",
      "args": [
        "-y",
        "vibe-check-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Cursor utilise le même schéma mcpServers que Claude Desktop. La config projet l'emporte sur la globale.

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "vibe-check": {
      "command": "npx",
      "args": [
        "-y",
        "vibe-check-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Cliquez sur l'icône MCP Servers dans la barre latérale Cline, puis "Edit Configuration".

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "vibe-check": {
      "command": "npx",
      "args": [
        "-y",
        "vibe-check-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Même format que Claude Desktop. Redémarrez Windsurf pour appliquer.

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "vibe-check",
      "command": "npx",
      "args": [
        "-y",
        "vibe-check-mcp-server"
      ]
    }
  ]
}

Continue utilise un tableau d'objets serveur plutôt qu'une map.

~/.config/zed/settings.json
{
  "context_servers": {
    "vibe-check": {
      "command": {
        "path": "npx",
        "args": [
          "-y",
          "vibe-check-mcp-server"
        ]
      }
    }
  }
}

Ajoutez dans context_servers. Zed recharge à chaud à la sauvegarde.

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

Une seule ligne. Vérifiez avec claude mcp list. Supprimez avec claude mcp remove.

Cas d'usage

Usages concrets : vibe-check-mcp-server

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

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

Quand l'utiliser : The agent is about to delete files, run a migration, or deploy — you want a second opinion.

Déroulement
  1. Invoke vibe_check on the plan
    Before running the migration, call vibe_check on this plan: [paste]. What could go wrong?✓ Copié
    → Pushback list: unchecked assumptions, missing rollback, scope creep
  2. Resolve or ignore each concern explicitly
    Address each concern — either mitigate or explicitly dismiss as out of scope.✓ Copié
    → Annotated plan ready to run

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

Pièges
  • Agent dismisses all concerns rubber-stamp style — Require the agent to restate each concern and the specific mitigation
Combiner avec : sequentialthinking-tools

Enforce session rules with vibe-check's constitution

👤 Teams sharing agent workflows ⏱ ~10 min intermediate

Quand l'utiliser : You want certain rules (never push to main, always write tests first) enforced across a session.

Déroulement
  1. 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.✓ Copié
    → Rules acknowledged; subsequent violations get interrupted
  2. Inspect when in doubt
    Call check_constitution to see what's currently in effect.✓ Copié
    → Current rules list

Résultat : 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

Quand l'utiliser : The agent made a classic mistake; you want it not to repeat.

Déroulement
  1. Log the lesson
    Call vibe_learn with: mistake='deleted prod table without snapshot', lesson='always take a snapshot before DDL on prod'.✓ Copié
    → Lesson stored for the session
  2. Rely on it later
    (later in same session) Attempt a DDL — vibe_check surfaces the stored lesson✓ Copié
    → Interrupt with the relevant past lesson

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

Combinaisons

Associez-le à d'autres MCPs pour un effet X10

Plan + pushback loop

Plan with sequentialthinking_tools, then call vibe_check on the plan before executing step 1.✓ Copié
vibe-check + overture

Visual plan + vibe-check layer

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

Outils

Ce que ce MCP expose

OutilEntréesQuand appelerCoût
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

Coût et limites

Coût d'exécution

Quota d'API
Uses your chosen LLM's quota
Tokens par appel
500-3000 for vibe_check
Monétaire
LLM token cost only
Astuce
Only vibe_check on substantive plans — skipping it on trivial edits saves tokens

Sécurité

Permissions, secrets, portée

Stockage des identifiants : LLM API key in env (OPENAI_API_KEY, ANTHROPIC_API_KEY, etc.)
Sortie de données : Only to your configured LLM provider

Dépannage

Erreurs courantes et correctifs

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 autres

AlternativeQuand l'utiliserCompromis
sequentialthinking-toolsYou want planning, not pushbackDifferent shape — no adversarial second model
overtureYou want visual gating instead of text pushbackHeavier setup

Plus

Ressources

📖 Lire le README officiel sur GitHub

🐙 Voir les issues ouvertes

🔍 Parcourir les 400+ serveurs MCP et Skills