Vibe-Coder

Provides an MCP server that manages feature clarification, PRD generation, phased development, progress tracking, and document storage for LLM-based coding features.
  • typescript

0

GitHub Stars

typescript

Language

2 months ago

First Indexed

3 weeks ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

Vibe-Coder is an MCP server that guides LLM-driven feature development with a structured workflow. It helps you clarify requirements, generate PRDs and implementation plans, organize work into phases and tasks, and track progress while storing and retrieving documents for each feature.

How to use

You use Vibe-Coder by engaging with an MCP client to execute a guided feature development process. Start with feature clarification to capture purpose, users, and constraints. Have the client generate a PRD and implementation plan from the clarified requirements. Break the work into development phases and assign concrete tasks. As you progress, update phase statuses and task completions to keep everyone aligned. When a feature is complete, verify that all requirements are implemented and ready for use. Documents are stored automatically for quick access and can be retrieved or saved to custom paths.

How to install

Prerequisites: you need Node.js and npm installed on your machine. Ensure you have a compatible MCP client able to connect to an MCP server via stdio transport.

Install dependencies for the MCP server project, build, and run in development as needed.

Configuration and usage notes

The server stores generated documents by default under documents/{featureId}/ with filenames based on document type, such as prd.md and implementation-plan.md. You can customize where documents are saved by using the save document workflow to provide a target path. Retrieve a document path at any time to check whether a document has been saved to disk.

Storage and documents

Default storage location: documents/{featureId}/prd.md for the Product Requirements Document and documents/{featureId}/implementation-plan.md for the Implementation Plan. You can save documents to a custom location using the save_document tool.

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

Development workflow and prompts

Follow the phased development workflow: start with feature clarification, generate a PRD and implementation plan, create development phases, add tasks, and update statuses as work progresses. Use the provided prompts to structure feature planning and ensure consistency across features.

Tools and resources

The MCP server exposes a set of tools to manage the workflow. You can start a feature clarification, provide clarifications, generate PRDs, create phases, add tasks, update statuses, and retrieve or save documents. These tools help you automate and track every step of feature development.

Development setup and debugging

For development with auto-rebuild, you can use the watch command to rebuild as you modify source files. If you need to debug how MCP servers communicate, you can run an inspector tool to access debugging utilities through a browser-based interface.

Available tools

start_feature_clarification

Begin the feature clarification process by initiating guidance and collecting requirements.

provide_clarification

Answer clarification questions about a feature to refine its scope.

generate_prd

Generate a Product Requirements Document and an implementation plan based on clarified requirements.

create_phase

Create a development phase for a feature to organize work by milestones.

add_task

Add tasks to a development phase to specify work items.

update_phase_status

Update the status of a development phase as work progresses.

update_task_status

Update the completion status of a task.

get_next_phase_action

Get guidance on what to do next in the development workflow.

get_document_path

Get the path of a generated document for retrieval.

save_document

Save a document to a specific location.

Built by
VeilStrat
AI signals for GTM teams
© 2026 VeilStrat. All rights reserved.All systems operational