# Multi-Document RAG

> Use this tool when you need to process and generate text based on large collections of documents in various formats, such as PDF, DOCX, and images, and perform semantic searches across them. It solves problems of information retrieval, document analysis, and text generation by extracting content, creating vector embeddings, and handling large files. It takes in document collections and outputs generated text, vector embeddings, and search results, making it ideal for applications that require robust document processing and retrieval-augmented generation capabilities.

Canonical page: https://skillsregistry.net/skills/anuragb7-multi-document-rag  
JSON: https://api.skillsregistry.net/v1/skills/anuragb7-multi-document-rag

## Description

MCP-RAG is a server implementation that enables large file processing and retrieval-augmented generation capabilities for AI assistants. Developed by Anurag Bombarde, it provides tools for extracting content from various document formats (PDF, DOCX, PPTX, Excel, CSV, and images) with OCR support, creating vector embeddings using OpenAI or SentenceTransformer models, and performing semantic searches across document collections. The implementation features robust handling of large files through chunking strategies, multi-vector store support with ChromaDB and Milvus integration, and comprehensive document processing with enhanced OCR capabilities for scanned documents and images.

## Trust

- **Trust score (0–1):** 0.33
- **Verification tier:** scanned
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/anuragb7-multi-document-rag)
- **Repository:** <https://github.com/anuragb7/mcp-rag>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "anuragb7-multi-document-rag"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/anuragb7-multi-document-rag` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/anuragb7-multi-document-rag/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt