Vibe Check MCP Server

What does “Vibe Check” MCP Server do?

The Vibe Check MCP Server is designed as a sanity check tool for AI workflows, acting as a strategic pattern interrupt to prevent cascading errors and tunnel vision during complex development tasks. By integrating with AI assistants, it leverages the “Vibe Check” tool—backed by LearnLM 1.5 Pro (Gemini API) and fine-tuned for pedagogy and metacognition—to enhance workflow strategies and encourage reflective problem-solving. This server enables AI systems to pause, assess their current reasoning or approach, and adjust before proceeding, thus minimizing the risk of compounding mistakes and improving code quality and decision-making in automated or assisted development pipelines.

List of Prompts

• No explicit prompt templates are listed in the repository or documentation.

List of Resources

• No explicit resources are defined or documented in the repository.

List of Tools

• Vibe Check: A single tool call named “Vibe Check” that interacts with LearnLM 1.5 Pro (Gemini API), specifically crafted for interrupting potentially problematic AI reasoning chains and providing pedagogical/meta-cognitive feedback.

Use Cases of this MCP Server

• AI Workflow Sanity Checks: Interjects in AI-driven coding or task flows to assess reasoning, reducing the risk of tunnel vision and cascading logic errors.
• Teaching and Mentorship for Developers: Provides meta-cognitive feedback and guidance, supporting learning and reflection in complex problem-solving scenarios.
• Automated Review in Code Generation: Offers strategic breaks for review and assessment during automated code or content creation to ensure quality.
• Enhanced Error Prevention: Acts as a guardrail in workflows to halt propagation of initial mistakes through subsequent steps.
• Strategy Optimization for AI Agents: Enables AI assistants to self-assess and recalibrate strategies dynamically during long-running tasks.

How to set it up

Windsurf

1. Ensure you have Node.js and NPM installed.
2. Locate the configuration file for Windsurf (typically windsurf.config.json).
3. Add the Vibe Check MCP Server to the mcpServers object:

   {
     "mcpServers": {
       "vibe-check-mcp": {
         "command": "npx",
         "args": ["@vibe-check/mcp-server@latest"]
       }
     }
   }
   

4. Save the file and restart Windsurf.
5. Verify the server is running and accessible from the AI client.

Claude

1. Install prerequisites (Node.js, NPM).
2. Edit or create the configuration file (e.g., claude_desktop_config.json).
3. Add the MCP server with:

   {
     "mcpServers": {
       "vibe-check-mcp": {
         "command": "npx",
         "args": ["@vibe-check/mcp-server@latest"]
       }
     }
   }
   

4. Save and restart Claude Desktop.
5. Confirm server availability in the MCP panel.

Cursor

1. Confirm Node.js is installed.
2. Edit the Cursor configuration file (e.g., cursor.config.json).
3. Insert:

   {
     "mcpServers": {
       "vibe-check-mcp": {
         "command": "npx",
         "args": ["@vibe-check/mcp-server@latest"]
       }
     }
   }
   

4. Save and restart Cursor.
5. Check for the MCP server in the tool/plugin list.

Cline

1. Make sure Node.js and NPM are installed.
2. Open the relevant configuration file.
3. Add:

   {
     "mcpServers": {
       "vibe-check-mcp": {
         "command": "npx",
         "args": ["@vibe-check/mcp-server@latest"]
       }
     }
   }
   

4. Save and restart Cline.
5. Confirm the MCP server appears in available integrations.

Securing API Keys with Environment Variables:

• Use a .env file as shown in .env.example:

  GEMINI_API_KEY=your_google_gemini_api_key
  

• In your configuration, you may reference environment inputs:

  {
    "env": {
      "GEMINI_API_KEY": "your_google_gemini_api_key"
    },
    "inputs": {}
  }
  

How to use this MCP inside flows

Using MCP in FlowHunt

To integrate MCP servers into your FlowHunt workflow, start by adding the MCP component to your flow and connecting it to your AI agent:

Click on the MCP component to open the configuration panel. In the system MCP configuration section, insert your MCP server details using this JSON format:

{
  "vibe-check-mcp": {
    "transport": "streamable_http",
    "url": "https://yourmcpserver.example/pathtothemcp/url"
  }
}

Once configured, the AI agent is now able to use this MCP as a tool with access to all its functions and capabilities. Remember to change “vibe-check-mcp” to whatever the actual name of your MCP server is and replace the URL with your own MCP server URL.

Overview

Roots support: Not mentioned.

I would rate this MCP server a 5/10. It has a clear purpose, open license, and basic tooling, but lacks comprehensive documentation for prompts, resources, and advanced MCP features (roots, sampling).

MCP Score