# RAG Anything

> Use this tool when you need to process and query large directories of documents with multimodal content, including images, tables, and text, to extract insights and build knowledge bases. It solves problems related to document analysis, research workflows, and AI assistant development by providing efficient and advanced retrieval-augmented generation capabilities. With support for multiple file formats and batch processing, it is ideal for use cases that require automated document understanding and retrieval, such as knowledge base construction and AI-powered research assistance.

Canonical page: https://skillsregistry.net/skills/rag-anything  
JSON: https://api.skillsregistry.net/v1/skills/rag-anything

## Description

This MCP server provides AI assistants with comprehensive RAG (Retrieval-Augmented Generation) capabilities for processing and querying directories of documents using the raganything library with full multimodal support. Built by Jesse Merhi using Python with LightRAG for graph-based retrieval, it supports end-to-end document processing with multimodal content extraction including images, tables, equations, and text across multiple file formats (PDF, DOCX, PPTX, TXT, MD), batch processing of entire directories, and advanced querying with multiple modes (hybrid, local, global, naive, mix, bypass). The implementation features persistent RAG instances per directory for efficient re-querying, concurrent processing with configurable workers, GPT-4V integration for image analysis, and OpenAI API compatibility with custom endpoints, making it valuable for research workflows, document analysis, knowledge base construction, and building AI assistants that need advanced document understanding and retrieval capabilities without manual processing.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** media
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/rag-anything)
- **Repository:** <https://github.com/jesse-merhi/rag-anything-mcp>

## 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": "rag-anything"
    }
  }
}
```

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