# PDF RAG MCP Server

> Use this tool when you need to search and extract information from PDF documents using intelligent semantic search and question-answering capabilities. It solves problems related to information retrieval from scanned or digital PDFs, supporting OCR and keyword search with accurate source tracking. Ideal for use cases requiring efficient document analysis and insight generation from large PDF collections.

Canonical page: https://skillsregistry.net/skills/wesleygriffin-pdfrag  
JSON: https://api.skillsregistry.net/v1/skills/wesleygriffin-pdfrag

## Description

Enables intelligent search and question-answering over PDF documents using semantic similarity and keyword search. Supports OCR for scanned PDFs, persistent vector storage with ChromaDB, and maintains source tracking with page numbers.

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/cjxg6qe1zj)
- **Repository:** <https://github.com/wesleygriffin/pdfrag>

## 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": "wesleygriffin-pdfrag"
    }
  }
}
```

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