1. Conduid
  2. AI
  3. Go RAG
MCP server · AI

Go RAG

by · github.com/gamma-omg/go-rag

MCP server for RAG written in Go

Unclaimed MIT last commit 11 months ago ai
InstallView source
51Fair

Scored 5 months ago · breakdown

About Go RAG

Go RAG is an MCP server published by gamma-omg in the AI category: mCP server for RAG written in Go.

The repository has 1 stars and 0 forks, with the last commit 11 months ago. Six months or more without a commit doesn't mean the server is broken, but check the open issues before depending on it in production.

Install

From source
git clone https://github.com/gamma-omg/go-rag

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about Go RAG

Powered by Claude · Grounded in docs

I know everything about Go RAG. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

Static checks derived from the repository 5 days ago. Heuristics on the source, not an audit.

  • ✓README presentThe repository ships documentation.
  • ✓License declaredUsable under a stated license.
  • ✓Tests presentA test suite exists in the repository.
  • ✓Dependencies pinnedA lockfile pins dependency versions.
  • ✓No dynamic code executionSource scan found no eval, dynamic Function, or shell execution.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

Go RAG

Go RAG is a Retrieval-Augmented Generation server that implements the Model Context Protocol (MCP) to provide document search capabilities for AI assistants. Built in Go, it allows AI models to search through your documents to provide more accurate, contextually relevant answers.

Features

  • Document Processing: Automatically indexes documents from a specified directory
  • Real-time Monitoring: Watches for file changes and updates the index automatically
  • Efficient Chunking: Splits documents into optimally sized chunks with configurable overlap
  • Vector Database Integration: Uses Chroma DB for efficient semantic search
  • MCP Implementation: Exposes search capabilities via the Model Context Protocol
  • Multiple Embedding Models: Supports both OpenAI and Google Gemini embeddings
  • Universal Document Support: Reads various document formats including PDF, DOCX, ODT, TXT, and more

Prerequisites

  • Go 1.23 or later
  • Docker and Docker Compose (for running ChromaDB)
  • OpenAI API key or Google Gemini API key

Quick Start

  1. Clone the repository:

    git clone https://github.com/gamma-omg/go-rag.git
cd go-rag

  2. Configure your settings:

    cp cfg/template.yaml cfg/config.yaml

    Edit cfg/config.yaml to set your API keys and other preferences.

  3. Start the tool:

    docker-compose up -d

  4. MCP server is now available at (the port can be changed in config.yaml)

    http://localhost:3001/sse

Cursor

To make this tool avaialbe in Cursor, go to Settings -> MCP -> Add new global MCP server and use this configuration:

"mcpServers": {
    "rag-mcp": {
        "url": "http://localhost:3001/sse"
    }
}

README fetched from the repository 5 days ago. The original is authoritative.

Questions

About Go RAG

How do I install Go RAG?

No package has been published for this server, so install it from source: clone the repository and follow its README.

Is Go RAG safe to use with an AI agent?

Its trust score is 51 out of 100 (fair). It passes 5 of the 6 static security checks run so far; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is Go RAG still maintained?

The last commit was 11 months ago. That's long enough that you should check whether the maintainer is responding to issues before depending on it.