skills.rest
Aradotso
AradotsoOFFICIAL
Explore all skills by this author →
Website𝕏@aradotsoGitHub

modular-rag-mcp-server

Deploy a modular RAG pipeline with hybrid retrieval via MCP.

7|2|Updated May 16, 2026
Search Tags:#embeddings#rag#mcp#dashboard#hybrid search#vector store#rag evaluation
One-click install
npx skills add https://github.com/Aradotso/mcp-skills --skill modular-rag-mcp-server
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: modular-rag-mcp-server
Source: https://github.com/Aradotso/mcp-skills/tree/main/skills/modular-rag-mcp-server
Command: npx skills add https://github.com/Aradotso/mcp-skills --skill modular-rag-mcp-server

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

It eliminates the friction of building and operating a Retrieval-Augmented Generation (RAG) system you can plug into AI assistants via Model Context Protocol (MCP), so questions can reliably pull from your documents instead of guessing.

Core Features & Use Cases

  • Ingestion Pipeline: Converts PDFs to Markdown, chunks content, generates embeddings, and builds a vector index with multimodal image captioning.
  • Hybrid Retrieval: Combines dense (semantic) + sparse (BM25) search using RRF fusion, with optional reranking for better relevance.
  • MCP Tools for Assistants: Exposes knowledge-hub operations like querying and collection/document introspection for Claude Desktop and other MCP clients.
  • Dashboard + Observability: Provides a Streamlit dashboard for ingestion and query tracking plus white-box tracing to debug performance regressions.
  • Evaluation with Ragas: Runs regression-style evaluation using Ragas metrics to validate improvements over time.

Quick Start

Run the MCP server and point your assistant’s MCP configuration to the project’s server entry so you can query your RAG collections immediately.

Frequently Asked Questions about modular-rag-mcp-server

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I expose my organization's documents to an AI assistant using MCP and RAG?▼

You can expose documents to an AI assistant using MCP by deploying a modular RAG pipeline that handles ingestion, generates embeddings, and implements knowledge-hub tools for querying and document introspection.

What is hybrid retrieval and how does RRF fusion improve RAG search results?▼

Hybrid retrieval combines dense semantic search with sparse BM25 search using Reciprocal Rank Fusion (RRF), optionally applying reranking to improve document relevance and reduce retrieval noise in RAG systems.

How do I evaluate RAG performance regressions over time?▼

You can evaluate RAG performance by running regression-style evaluation using Ragas metrics, which validate retrieval and generation improvements over time across document collections.

Does this RAG pipeline support PDF ingestion and multimodal content?▼

Yes, the ingestion pipeline converts PDFs to Markdown, chunks content, builds a vector index, and includes multimodal image captioning to process visual content within documents.

Can I use a Streamlit dashboard to monitor RAG ingestion and queries?▼

Yes, a Streamlit dashboard provides ingestion and query tracking plus white-box tracing to debug RAG performance regressions across your document collections.

Do I need specific vector store or LLM components to use this modular RAG server?▼

No, the server supports configurable pluggable components, allowing you to swap the LLM, embeddings, reranker, splitter, vector store, and evaluator to fit your existing stack.

Related Skills

Explore More Software Engineering Skills→
bethanychamberlainbethanychamberlain
2

rag

Configure LibreChat's RAG pipeline for document ingestion and retrieval.

Community
Advanced
hpsgdhpsgd

rag-pipeline

Design an end-to-end RAG pipeline for document QA and knowledge retrieval.

Official
Advanced
rennerenne

ha-mcp

Install, configure, and operate the ha-mcp Model Context Protocol server for Home Assistant control.

Community
Advanced
juanrejuanre
6

hybrid-search

Merge semantic and keyword retrieval with configurable alpha and RRF fusion in Python.

Community
Intermediate