# Lizeur (PDF OCR)

> Use this tool when you need to extract readable text from PDF documents with high OCR accuracy, solving problems in document analysis and content extraction. It takes PDF files as input and returns clean markdown text as output, allowing for easy integration with AI workflows. Ideal for use cases where AI assistants require access to PDF content, such as text summarization, question answering, or information retrieval.

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

## Description

Lizeur is an MCP server that enables AI assistants to extract and read content from PDF documents using Mistral AI's OCR capabilities. Built with FastMCP, it provides intelligent caching to avoid re-processing documents and returns clean markdown text for easy integration with AI workflows. The implementation uploads PDFs to Mistral's OCR service, processes the first page, caches results locally for future use, and handles file cleanup automatically, making it valuable for document analysis, content extraction, and AI assistants that need to work with PDF files where OCR accuracy is important.

## Trust

- **Trust score (0–1):** 0.93
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/lizeur-pdf-ocr)
- **Repository:** <https://github.com/silverbzh/lizeur>

## 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": "lizeur-pdf-ocr"
    }
  }
}
```

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