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.
npx skills add Nicvank/paddleocr-mcp --skill skillgit clone --depth 1 https://github.com/Nicvank/paddleocr-mcpWrote 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.
[](https://agentmods.dev/skills/nicvank/paddleocr-mcp/skill)<a href="https://agentmods.dev/skills/nicvank/paddleocr-mcp/skill"><img src="https://agentmods.dev/badge/skills/nicvank/paddleocr-mcp/skill/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/nicvank/paddleocr-mcp/skill"><img src="https://agentmods.dev/badge/skills/nicvank/paddleocr-mcp/skill.svg" alt="Reviewed on agentmods" width="80" height="20"></a>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.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00033 | $0.01925 |
| Opus 5.5 | $0.00013 | $0.00770 |
| Sonnet 5.5 | $0.00007 | $0.00385 |
| Haiku 4.5 | $0.00003 | $0.00193 |
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 1mo 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.
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
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en、japan、korean、fr、german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
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.
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.
- 1mo ago First seen · 195 lines · 33 tokens per session scan A eeb13d5da011
paddleocr-mcp is a skill published in the GitHub repository Nicvank/paddleocr-mcp (2 stars, last pushed 2mo ago), licensed MIT. It adds 33 tokens to every session and 1,925 once invoked, about $0.0001 per session on Opus 5.5. 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.
Other skills, from other repositories
paddleocr-doc-parsing
A document-parsing tool configuration for extracting structured Markdown or JSON from complex PDFs and document images, including tables, formulas, charts, and multi-column pages.
paddleocr-text-recognition
An optical character recognition tool configuration for extracting text from images, photos, scans, screenshots, and scanned PDFs. OCR means converting text visible in an image into machine-readable text.
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…
format-specific-extraction
ZIP archive → Security validation → XML parsing → Text + tables + metadata.
pdf-table-to-excel
A workflow for turning tables in PDF files into Excel workbooks, with one sheet per table and supporting images and quality notes. It uses MinerU, a tool that extracts content from PDFs, and needs an image-reading model to check the results.
paddleocr-doc-parsing
A document-reading skill that turns complex PDFs and document images into structured Markdown or JSON. It can preserve tables, formulas, figures, and reading order.