# PaddleOCR MCP Server

> Use this tool when you need to recognize and parse text from various sources, including handwritten documents and complex layouts. It solves problems such as extracting data from invoices, receipts, and other documents with multiple text types and formats. The PaddleOCR MCP Server takes in image or document inputs and outputs parsed text data, making it ideal for automating data entry and document processing tasks.

Canonical page: https://skillsregistry.net/skills/paddlepaddle-paddleocr  
JSON: https://api.skillsregistry.net/v1/skills/paddlepaddle-paddleocr

## Description

Multiple text-type recognition, handwriting recognition, and high-precision parsing of complex documents.

## Trust

- **Trust score (0–1):** 0.94
- **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:** [Glama](https://glama.ai/mcp/servers/f3ids56oy4)
- **Repository:** <https://github.com/PaddlePaddle/PaddleOCR>

## 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": "paddlepaddle-paddleocr"
    }
  }
}
```

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