Vibe-Coder MCP Server

A Model Context Protocol server designed to streamline LLM-based coding workflows with structured development processes.

Overview

The Vibe-Coder MCP Server provides a structured framework for feature development, enabling organized, clean, and safe coding practices. It offers tools for feature clarification, documentation generation, phased development, and progress tracking.

Features

Resources

• Feature details, PRDs, and implementation plans
• Progress reports and status tracking
• Phase and task details

Tools

• start_feature_clarification: Initiates the feature clarification process
• provide_clarification: Answers clarification questions about a feature
• generate_prd: Generates a Product Requirements Document and implementation plan
• create_phase: Creates a development phase for a feature
• add_task: Adds tasks to a development phase
• update_phase_status: Updates the status of a phase
• update_task_status: Updates the completion status of a task
• get_next_phase_action: Provides guidance on the next steps
• get_document_path: Retrieves the path of a generated document
• save_document: Saves a document to a custom location

Prompts

• feature-planning: A prompt template for planning feature development

Document Storage

The server includes a hybrid document storage system that:
1. Automatically saves generated documents (PRDs, implementation plans) to files
2. Maintains an in-memory copy for quick access
3. Allows clients to retrieve document paths and save to custom locations

Default Storage Location

Documents are stored in the documents/{featureId}/ directory by default:
- documents/{featureId}/prd.md: Product Requirements Document
- documents/{featureId}/implementation-plan.md: Implementation Plan

Custom Storage

Use the save_document tool to save documents to custom locations:

{
  "featureId": "feature-123",
  "documentType": "prd",
  "filePath": "/custom/path/feature-123-prd.md"
}

Path Retrieval

Retrieve document paths using the get_document_path tool:

{
  "featureId": "feature-123",
  "documentType": "prd"
}

Development

Install dependencies:

npm install

Build the server:

npm run build

For development with auto-rebuild:

npm run watch

Installation

To use with compatible MCP clients:

On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
On Windows: %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "vibe-coder-mcp": {
      "command": "/path/to/vibe-coder-mcp/build/mcp-server.js"
    }
  }
}

Debugging

Use the MCP Inspector for debugging:

npm run inspector

Implementation Notes

The server is built using the McpServer class from the Model Context Protocol TypeScript SDK. Example implementation:

import { McpServer, ResourceTemplate } from "@modelcontextprotocol/sdk/server/mcp.js";
import { StdioServerTransport } from "@modelcontextprotocol/sdk/server/stdio.js";

// Create an MCP server
const server = new McpServer({
  name: "Vibe-Coder",
  version: "0.3.0"
});

// Add a resource
server.resource(
  "features-list",
  "features://list",
  async (uri) => ({ /* ... */ })
);

// Add a tool
server.tool(
  "start_feature_clarification",
  { /* parameters schema */ },
  async (params) => ({ /* ... */ })
);

// Add a prompt
server.prompt(
  "feature-planning",
  { /* parameters schema */ },
  (params) => ({ /* ... */ })
);

// Start the server
const transport = new StdioServerTransport();
await server.connect(transport);

Workflow

1. Feature Clarification: Gather requirements and understand the feature's purpose, target users, and constraints.
2. Documentation: Generate a PRD and implementation plan based on clarified requirements.
3. Phased Development: Break down the implementation into logical phases with clear tasks.
4. Progress Tracking: Monitor task and phase completion to guide development.
5. Completion: Verify that all requirements have been implemented and the feature is ready for use.

About

A MCP server designed to assist with Vibecoding.

Resources

• Readme
• Activity

Stars

2 stars

Watchers

1 watching

Forks

1 fork

Languages

• TypeScript 52.1%
• JavaScript 47.9%