mcpField
V
Vibe Coder MCP Server - v4 Final Release

Vibe Coder MCP Server - v4 Final Release

Local
github.com/jsscarfoDeveloper Tools1Updated 80w ago
Repository

About Vibe Coder MCP Server - v4 Final Release

Vibe Coder MCP Server v4 adds contextual retrieval tools for LLM-based assistants that need memory and prompt processing. Its ACRS combines semantic search, caching, and stepwise reasoning; this release is final, with v5 developed in a separate repository.

Key features

  1. 01Store and retrieve contextual memory
  2. 02Find related content semantically
  3. 03Cache to reduce LLM calls
  4. 04Break complex problems into steps
  5. 05Show retrieval performance metrics

Use cases

  1. 01Save and retrieve relevant information for an assistant
  2. 02Process requests using contextual information
  3. 03Enhance prompts for LLMs

MCP support

As an MCP server, it exposes ACRS tools for memory, context-aware request processing, prompt enhancement, and retrieval metrics.

#vibe-coder#mcp-server#automatic-retrieval

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

No install method listed yet

We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.

Repository

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Vibe Coder MCP Server - v4 Final Release

IMPORTANT NOTICE: This is the final v4 release of the Vibe Coder MCP Server, which includes the Automatic Contextual Retrieval System (ACRS) tools. Development has moved to v5 in a separate repository. This version is being made available to the community as a stable, feature-complete release.

New in v4: Automatic Contextual Retrieval System (ACRS)

The v4 release introduces the Automatic Contextual Retrieval System, which enhances AI assistant capabilities through:

  • Contextual memory: Stores and retrieves relevant information based on the current context
  • Advanced caching: Reduces redundant LLM calls and improves response times
  • Semantic search: Finds related content based on meaning rather than exact text matching
  • Sequential thinking: Breaks down complex problems into manageable steps

These tools enable more coherent, context-aware interactions with LLM-based assistants.

Getting Started with GitHub Version

Quick Installation

  1. Clone the repository:

    git clone https://github.com/jsscarfo/vibe-coder-mcp-v4.git
cd vibe-coder-mcp-v4

  2. Setup:

    • For Windows: setup.bat
    • For macOS/Linux: 
      chmod +x setup.sh
./setup.sh

  3. Configure OpenRouter API Key:

    • Create a .env file by copying .env.example
    • Add your OpenRouter API key to the .env file

  4. Integrate with your AI Assistant:

    • Update your AI assistant's MCP configuration to include Vibe Coder
    • See the full Setup Guide below for detailed instructions
ACRS Tools Usage

To use the Automatic Contextual Retrieval System tools:

  1. Add memory entries:

    Add to memory: [content to remember]

  2. Process requests with contextual enhancement:

    Process request [your request] with context

  3. Enhance prompts for LLMs:

    Enhance prompt: [your prompt]

  4. Get performance metrics:

    Get retrieval metrics

See the detailed documentation below for more information.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.