# PDF Reader

> Use this tool when you need to quickly extract text from PDF files or list available PDF documents in a directory. It solves problems of accessing and processing PDF content through AI assistants, ideal for simple text extraction and document querying tasks. The PDF Reader takes PDF files as input and outputs clean Markdown text, making it suitable for workflows requiring fast and straightforward document processing.

Canonical page: https://skillsregistry.net/skills/pdf-reader  
JSON: https://api.skillsregistry.net/v1/skills/pdf-reader

## Description

Local MCP server that extracts text from PDF files using Docling for document conversion and pypdfium2 as the backend. Built by MLExpert.io, it provides two core tools: listing available PDF files in a data directory and converting PDF content to clean Markdown format with OCR and table structure processing disabled for faster performance. Designed for workflows where users need to quickly access and process PDF documents through AI assistants like Claude Desktop or Cursor without complex document analysis features, making it ideal for simple text extraction and document querying tasks.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-02

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** productivity
- **Updated:** 2026-09-02

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/pdf-reader)
- **Repository:** <https://github.com/mlexpertio/mcp-pdf-reader>

## 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": "pdf-reader"
    }
  }
}
```

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