uocr

uocr is a skill for Claude Code from tinygone/unlimited-ocr-mcp-server. It costs 84 tokens per session (1,278 once invoked), scanned A, original, MIT.

An OCR skill for reading text from images. OCR means turning text in screenshots, scans, photos, or document images into computer-readable text; it can handle one image or multiple pages.

In plain words
What is it for?
Reading invoices, contracts, forms, screenshots, and other image-based documents. It requires a local OCR service running at http://127.0.0.1:10000 and an activated uocr environment.
Why use it?
It prevents the agent from guessing what an image says and provides text that can then be summarized, translated, structured, or used to answer questions.

Skill for Claude Code

Written for Claude Code: installed under .claude/.

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/tinygone/unlimited-ocr-mcp-server/uocr
Any agent
npx skills add tinygone/unlimited-ocr-mcp-server --skill uocr
Clone the repo
git clone --depth 1 https://github.com/tinygone/unlimited-ocr-mcp-server

Made for: Claude Code.

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 uocr

README.md
[![agentmods](https://agentmods.dev/badge/skills/tinygone/unlimited-ocr-mcp-server/uocr.svg)](https://agentmods.dev/skills/tinygone/unlimited-ocr-mcp-server/uocr)
Your own site
<a href="https://agentmods.dev/skills/tinygone/unlimited-ocr-mcp-server/uocr"><img src="https://agentmods.dev/badge/skills/tinygone/unlimited-ocr-mcp-server/uocr.svg" alt="Measured on agentmods" height="20"></a>
Per session 84 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 1,278 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 1 finding. 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 $0.00084 $0.01278
Opus 5 $0.00042 $0.00639
Sonnet 5 $0.00017 $0.00256
Haiku 4.5 $0.00008 $0.00128

Measured 5d ago against content hash 8e68bb910eaf, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-05, from the pricing page.

Security

Grade A, and why

uocr scanned grade A with 1 finding 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

- 验证:`curl http://127.0.0.1:10000/v1/models` 应返回模型列表
.claude/skills/uocr/SKILL.md · 115 lines

How it starts

The opening of the file, as written. The whole thing — 115 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UOCR Skill

⚠️ 前置条件(必须满足才能用)

本 Skill 调用的 mcp__uocr__ocr_image / mcp__uocr__ocr_multi 工具,背后依赖一个本地 OCR 服务,必须先启动:

  1. OCR 服务必须在线:另一个终端运行 python serve_ocr.py,监听 http://127.0.0.1:10000
    • 验证:curl http://127.0.0.1:10000/v1/models 应返回模型列表
    • 服务未启动时调用会卡住直到超时(默认 1800s)
  2. 环境变量(首次下载模型需要):HF_ENDPOINT=https://hf-mirror.com(国内)
  3. conda 环境:需激活 uocr 环境(含 PyTorch + transformers)

详见项目根目录 README.md

技能目标

使用 uocr MCP server 识别图片中的文字内容,并在拿到识别结果后,按用户原始诉求继续处理(总结、翻译、结构化、回答问题等)。

核心原则:不要在调用 OCR 工具前猜测图片内容。

触发条件

当任务中出现以下任一情况时,必须使用本技能:

  • 用户提供了图片(截图、扫描件、拍照件、文档图片等)
  • 用户要求"识别这张图""看看图里写了什么""OCR 一下""读取图片"等
  • 任务需要从图片中提取文字信息(例如发票、合同、表单、UI 截图等)

可用工具(由 uocr MCP server 提供)

1. ocr_image — 识别单张图片

参数:

  • image_path推荐):本地图片绝对路径,例如 D:/docs/page.png
  • image_base64:图片 base64 编码(不带 data: 前缀);没有路径时使用
  • prompt:识别任务描述,默认 "document parsing."

调用示例:

{
  "image_path": "D:/aiworkspace/uocr-workspace/inputs/1.jpg"
}

2. ocr_multi — 识别多张图片(多页文档)

参数:

  • image_paths:图片路径列表,例如 ["page1.png", "page2.png"]
  • prompt:任务描述,默认 "Multi page parsing."

调用示例:

{
  "image_paths": [
    "D:/docs/page1.png",
    "D:/docs/page2.png"
  ]
}

多张图会一起识别,能更好地保留跨页上下文,适合多页扫描件、PDF 转出的多张图。

执行流程

  1. 判断工具

    • 单张图 → ocr_image
    • 多张图(≥2)→ ocr_multi
  2. 构造参数

    • 优先使用 image_path(本地绝对路径)
    • 路径需为绝对路径,正斜杠 / 或双反斜杠 \\ 均可
    • 只有在拿不到本地路径时,才退而使用 image_base64(不带 data: 前缀)
  3. 调用工具:调用对应的 mcp__uocr__ocr_imagemcp__uocr__ocr_multi

  4. 处理结果

    • 工具返回的是纯文本识别结果(可能附带一段结构化 JSON)
    • 不要把原始 JSON 直接丢给用户,应整理成易读的形式
    • 拿到结果后,继续按用户的原始诉求处理:
      • 仅识别 → 给出识别文字
      • 要求总结 → 总结
      • 要求翻译 → 翻译
      • 要求结构化 → 输出表格 / JSON / Markdown
      • 要求回答问题 → 基于识别内容作答
  5. 格式建议

    • 按图片版面结构组织(标题、正文、表格、底部按钮等)
    • 繁体内容可附简体摘要
    • 主动给出后续可选操作(翻译、结构化导出、对比其他截图等)

注意事项

  • 不要在调用 OCR 工具前猜测或描述图片内容
  • 不要把工具返回的原始 JSON 直接作为最终答复
  • ✅ 单图用 ocr_image,多图用 ocr_multi
  • ✅ 优先 image_path,必要时才用 image_base64
  • image_base64 必须去掉 data:image/...;base64, 前缀
  • ✅ 拿到结果后必须做二次加工,不能止步于返回原文

Read the full file on GitHub · 115 lines

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 · 115 lines · 84 tokens per session scan A 8e68bb910eaf

Subscribe to this mod's changes

uocr is a skill published in the GitHub repository tinygone/unlimited-ocr-mcp-server (0 stars, last pushed 1mo ago), licensed MIT. It adds 84 tokens to every session and 1,278 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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

orbit-notion

Open Orbit briefing skill — selected by the Orbit pipeline when Notion is the user's only connected connector, or when the user explicitly scopes their daily digest to Notion. Pulls the past 24 hours of document edits, comments, mentions, and database row changes from the user's authenticated Notion connection and…

nexu-io/open-design · 117 tokens

instrument-data-to-allotrope

Convert laboratory instrument output files (PDF, CSV, Excel, TXT) to Allotrope Simple Model (ASM) JSON format or flattened 2D CSV. Use this skill when scientists need to standardize instrument data for LIMS systems, data lakes, or downstream analysis. Supports auto-detection of instrument types. Outputs include full…

anthropics/knowledge-work-plugins · 123 tokens

baoyu-youtube-transcript

Downloads YouTube video transcripts/subtitles and cover images by URL or video ID. Supports multiple languages, translation, chapters, and speaker identification. Caches raw data for fast re-formatting. Use when user asks to "get YouTube transcript", "download subtitles", "get captions", "YouTube字幕", "YouTube封面"…

JimLiu/baoyu-skills · 107 tokens

feishu

Work with Feishu or Lark bots, docs, sheets, bitables, approval flows, and OpenAPI/MCP setup without hardcoding credentials.

Hmbown/CodeWhale · 33 tokens

gog-slides

Google Slides operations through gog.

openclaw/gogcli · 11 tokens

read

Reads URLs and PDFs by fetching source content, defaulting to concise summaries for plain read requests and clean Markdown when asked to convert, save, quote, cite, or feed downstream work. Use when users ask in any language to read, fetch, check, summarize, quote, cite, convert, or save a URL or PDF. Not for local…

tw93/Waza · 78 tokens