paddleocr-mcp

paddleocr-mcp is a skill for Claude Code, Codex from Nicvank/paddleocr-mcp. It costs 33 tokens per session (1,925 once invoked), scanned A, original, MIT.

A local document-reading service that extracts text from images and PDFs, including tables, screenshots, and structured page content. OCR means recognizing printed or handwritten text in an image.

In plain words
What is it for?
It is for reading screenshots, invoices, receipts, images, and PDF documents, and for extracting their text, tables, and layout.
Why use it?
It turns scanned or pictured documents into text and Markdown that an agent can inspect, without sending the files to a public OCR service.

Skill for Claude CodeCodex

Written for no agent in particular: nothing here depends on one.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/nicvank/paddleocr-mcp/skill
Any agent
npx skills add Nicvank/paddleocr-mcp --skill skill
Clone the repo
git clone --depth 1 https://github.com/Nicvank/paddleocr-mcp

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for paddleocr-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/nicvank/paddleocr-mcp/skill.svg)](https://agentmods.dev/skills/nicvank/paddleocr-mcp/skill)
Your own site
<a href="https://agentmods.dev/skills/nicvank/paddleocr-mcp/skill"><img src="https://agentmods.dev/badge/skills/nicvank/paddleocr-mcp/skill.svg" alt="Measured on agentmods" height="20"></a>
Per session 33 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,925 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00033 $0.01925
Opus 5 $0.00016 $0.00962
Sonnet 5 $0.00007 $0.00385
Haiku 4.5 $0.00003 $0.00193

Measured 5d ago against content hash eeb13d5da011, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

paddleocr-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

skill/SKILL.md · 195 lines

How it starts

The opening of the file, as written. The whole thing — 195 lines — stays where its author put it; the contents beside it link to each section on GitHub.

PaddleOCR MCP Skill

English version

这是本地 PaddleOCR MCP Server 的 Agent 使用指南。服务使用 MCP Python SDK v2,图片和文档在服务所在机器上处理,不调用公共 OCR API。

前置条件

  • MCP Server 已安装并配置到 Agent 客户端;
  • 推荐使用项目虚拟环境中的 Python;
  • 推荐在安装阶段运行 python install.py --device auto,它会检测 nvidia-smi 并选择受支持的 CPU/GPU 依赖;
  • paddleocr-mcp doctor 可以检查 Python、依赖、设备和模型缓存;
  • 首次调用可能下载模型权重到 ~/.paddlex/official_models/

安装器当前支持 CUDA 11.8、12.6–12.8、12.9+(12.x)和 13.x 的官方 wheel 映射;未知版本在自动模式下回退 CPU,在强制 GPU 模式下报错。

可用工具

ocr_image

使用当前安装的 PaddleOCR 默认 OCR 管线(当前依赖线为 PP-OCRv6)处理普通图片。

参数:

{
  "image_path": "/absolute/path/to/image.png",
  "language": "ch"
}
  • image_path:必填,本地 PNG/JPEG/BMP/WebP/TIFF 路径;
  • language:可选,默认 ch,也可使用 enjapankoreanfrgerman 等 PaddleOCR 支持的语言。

返回结构:

{
  "engine": "PP-OCRv6 (latest installed PaddleOCR)",
  "source_name": "image.png",
  "elapsed_seconds": 1.234,
  "text": "recognized text",
  "blocks": [
    {"text": "recognized text", "score": 0.998, "bbox": [10, 20, 200, 60]}
  ]
}

适合截图、照片、发票、收据和简单布局的图片。

parse_document

使用当前安装的 PaddleOCR-VL 管线处理图片或 PDF,并返回结构化 Markdown。

参数:

{
  "image_path": "/absolute/path/to/document.pdf"
}

返回结构:

{
  "engine": "PaddleOCR-VL (latest installed PaddleOCR)",
  "source_name": "document.pdf",
  "elapsed_seconds": 12.345,
  "markdown": "# Document\n\n..."
}

适合 PDF、表格、多栏文档、复杂布局和需要保留结构的任务。它比 ocr_image 更慢、更占内存。

smart_ocr

自动选择 OCR 或文档解析管线:

{
  "image_path": "/absolute/path/to/file",
  "language": "ch",
  "force_model": "ocr"
}

路由规则:

force_model == "vl"       -> parse_document
force_model == "ocr"      -> ocr_image(仅适用于图片)
PDF                         -> parse_document
图片任一边 > 2000 像素     -> parse_document
其他图片                   -> ocr_image

如果用户不确定输入类型,优先使用 smart_ocr

Agent 决策规则

用户要求处理图片、截图、PDF 或文档
  |
  +-- 用户明确要求快速提取文字?
  |     +-- 是 -> ocr_image(普通图片)
  |     +-- 否
  |
  +-- 用户明确要求表格、版面、PDF 或 Markdown?
  |     +-- 是 -> parse_document
  |     +-- 否
  |
  +-- 输入类型或复杂度不确定?
        +-- 是 -> smart_ocr

Read the full file on GitHub · 195 lines

Files

What ships with it

1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 5d ago First seen · 195 lines · 33 tokens per session scan A eeb13d5da011

Subscribe to this mod's changes

paddleocr-mcp is a skill published in the GitHub repository Nicvank/paddleocr-mcp (2 stars, last pushed 1mo ago), licensed MIT. It adds 33 tokens to every session and 1,925 once invoked, about $0.0002 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

paddleocr-doc-parsing

Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表…

PaddlePaddle/PaddleOCR · 140 tokens

paddleocr-text-recognition

Use this skill whenever the user wants text extracted from images, photos, scans, screenshots, or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox coordinates. Strong accuracy for CJK, small print, and handwritten text. Trigger terms: OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字…

PaddlePaddle/PaddleOCR · 125 tokens

paddleocr-doc-parsing

Use this skill to extract structured Markdown/JSON from PDFs and document images—tables with cell-level precision, formulas as LaTeX, figures, seals, charts, headers/footers, multi-column layout and correct reading order. Trigger terms: 文档解析, 版面分析, 版面还原, 表格提取, 公式识别, 多栏排版, 扫描件结构化, 发票, 财报, 复杂 PDF, PDF转Markdown, 图表…

Aidenwu0209/PaddleOCR-Skills · 140 tokens

paddleocr-text-recognition

Use this skill whenever the user wants text extracted from images, photos, scans, screenshots, or scanned PDFs. Returns exact machine-readable strings with line-level text and optional bbox coordinates. Strong accuracy for CJK, small print, and handwritten text. Trigger terms: OCR, 文字识别, 图片转文字, 截图识字, 提取图中文字, 扫描识字, 识字…

Aidenwu0209/PaddleOCR-Skills · 125 tokens

paddleocr-skills-setup

Install and configure two PaddleOCR Agent Skills for text recognition and structured document parsing in Codex, Claude Code, GitHub Copilot, Cursor, OpenCode, OpenClaw, and other compatible agents. Use for OCR and image-to-text from screenshots, photos, scans, and PDFs; Chinese/CJK text and bounding boxes…

Aidenwu0209/PaddleOCR-Skills · 102 tokens

kreuzberg

Extract text, tables, metadata, and images from 91+ document formats (PDF, Office, images, HTML, email, archives, academic) using Kreuzberg. Use when writing code that calls Kreuzberg APIs in Python, Node.js/TypeScript, Rust, or CLI. Covers installation, extraction (sync/async), configuration (OCR, chunking, output…

kreuzberg-dev/kreuzberg-lts · 89 tokens