# PDF RAG MCP Server

> Use this tool when you need to extract meaningful information from complex, scanned, or poorly formatted PDF documents. It solves problems related to document analysis, information retrieval, and search by enabling the extraction, chunking, embedding, and searching of messy PDFs. This server takes in scanned, multi-column, and table-heavy PDFs as input and outputs searchable, structured data.

Canonical page: https://skillsregistry.net/skills/mbaranektech-pdf-rag-mcp  
JSON: https://api.skillsregistry.net/v1/skills/mbaranektech-pdf-rag-mcp

## Description

Enables RAG over messy PDFs — extract, chunk, embed, and search scanned, multi-column, and table-heavy documents.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/v14d8jc1jj)
- **Repository:** <https://github.com/MBaranekTech/pdf-rag-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": "mbaranektech-pdf-rag-mcp"
    }
  }
}
```

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