# PDF Processor

> Use this tool when you need to extract text content and recognize mathematical equations from PDFs, such as academic papers and technical documents. It takes URLs or PDF files as input and outputs extracted text and LaTeX equations, providing a valuable solution for researchers, students, and workflows requiring PDF processing. Ideal for use cases involving document analysis, equation recognition, and text extraction, this tool offers efficient and optimized performance with comprehensive error handling and configurable output options.

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

## Description

This MCP server provides PDF processing capabilities with advanced LaTeX equation extraction, enabling AI assistants to fetch PDFs from URLs, extract text content, and recognize mathematical equations from academic papers and technical documents. Built by Michael Levinson using Python with PyMuPDF for text extraction and pix2tex for LaTeX OCR, it offers optimized performance on Apple Silicon with fallbacks for other hardware, three-step workflow (fetch, process, read) to manage memory efficiently, and both standalone MCP server and FastAPI implementations for different integration needs. The implementation includes comprehensive error handling, configurable output directories, and specialized support for academic paper processing, making it valuable for researchers analyzing mathematical papers, students working with technical documents, and any workflow requiring extraction of both text and mathematical content from PDF sources.

## Trust

- **Trust score (0–1):** 0.84
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** iot-hardware
- **Updated:** 2026-09-19

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/pdf-processor)
- **Repository:** <https://github.com/michaellevinson/mcp_pdf_processor>

## 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-processor"
    }
  }
}
```

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