Ocr

com.auto-reader由 auto-reader.com 发布官方发布者v1.0.3更新于 Oct 24, 2026

Arabic-first OCR, translation and document extraction. First call mints a free trial key.

已验证Streamable HTTP可网页运行媒体与设计AI 与机器学习

概览

AI 生成的概览

远程 OCR 与文档 AI 服务，让助手从图片中读取文字、提取结构化字段并进行翻译，阿拉伯语支持尤为突出。

可以做什么
  • 用 GPU OCR 从图片中读取文字，支持阿拉伯语、波斯语、乌尔都语、竖排日文等 13 种以上语言，并可自动识别语言。
  • 识别漫画页面，按语言将日文、韩文条漫和中文漫画分派给对应的识别引擎。
  • 从发票、收据、身份证件或自定义 JSON 模式中提取结构化字段，每个字段返回取值、置信度和位置框。
  • 在多种语言之间翻译文本，可控制正式程度并给出备选译法，也可一次调用完成图片识别并逐行翻译。
  • 查询密钥等级、剩余额度和速率限制，并开通新的 API 密钥。
适用场景
适合需要读取扫描件、照片文档、标牌、收据或漫画页面的场景，尤其是阿拉伯语等非拉丁文字，或需要把扫描件转成结构化字段、译文而无需自建 OCR 流程时。
运行要求
通过 streamable HTTP 连接的远程 MCP 端点，无需本地运行时或安装包。持续使用需要 Auto-Reader API 密钥：首次调用会自动签发免费试用密钥，之后调用需以 api_key 参数传入该密钥；提供邮箱可解锁更大免费额度。需要能访问服务商 API 的网络。
安装前请注意
图片和文档会发送给第三方服务处理。该服务可自行创建 API 密钥，返回的密钥应妥善保存并当作机密处理。免费额度有限（无邮箱约每天 25 额度，提供邮箱约每天 250 额度），超出后可能涉及付费额度或订阅。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Ocr，将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/com.auto-reader%2Focr/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "ocr": {
      "type": "http",
      "url": "https://api.auto-reader.com/mcp"
    }
  }
}

README

Auto-Reader OCR — Arabic-first OCR & Document AI for agents

Extract text from images and PDFs (best-in-class Arabic, manga-aware Japanese, 13+ languages auto-detected), translate 100+ languages, pull structured fields from invoices/receipts/IDs — with Saudi ZATCA e-invoice QR validation — and get RAG-ready markdown or semantic chunks. Self-hosted, PDPL-compliant: documents are processed transiently and never stored.

No signup needed. Your first call auto-provisions a free trial key.

Add to Claude Code (10 seconds)

bash
claude mcp add --transport http auto-reader-ocr https://api.auto-reader.com/mcp

Registry: com.auto-reader/ocr · Tools: ocr_image, extract_document, translate_text, ocr_and_translate, get_usage, create_api_key.

Or plain HTTP (any agent, any language)

bash
curl -X POST https://api.auto-reader.com/signup      # -> {"api_key":"nsk_live_..."}curl -X POST https://api.auto-reader.com/v1/ocr \  -H "Authorization: Bearer $KEY" -F "[email protected]" -F "lang=auto"

Why agents pick this API

  • Arabic is the differentiator: RTL-aware layout, logical-order text, RTL-correct word boxes, Arabic-Indic digits — plus Arabic↔English code-switched documents.
  • format=markdown / format=chunks (title-bounded, tables kept whole) turn any scan into RAG input in one call; Accept: text/markdown returns a raw .md body.
  • extract_document returns {value, confidence, box} per field, sourced from OCR geometry — never model guesswork.

Site: https://ocr.auto-reader.com · العربية: https://ocr.auto-reader.com/ar

来源：README.md，提交 8bcaf28

工具

7

extract_document

Extract STRUCTURED FIELDS from a document image: invoices, receipts, ID cards — or any custom JSON schema you supply. Every field returns {value, confidence, box} where the confidence and box come from the OCR geometry (never model guesswork); absent fields are null. preset="zatca" additionally decodes the Saudi ZATCA e-invoice QR (TLV) and cross-validates it against the printed fields — use it for Saudi tax invoices. Arabic-first accuracy. 5 credits/page (zatca 7).

输入参数langpresetschemaapi_keyimage_base64必填

ocr_image

Extract text from an image with GPU OCR. Best-in-class Arabic (plus Persian/Urdu) accuracy, manga-aware vertical Japanese, and strong English, French, Spanish, German, Chinese, Korean, Russian, Italian and Portuguese — 13+ languages. Automatic language and script detection with lang="auto". Returns reading-order layout text (right-to-left aware, paragraph-gapped) that is ready to feed an LLM or show a human, plus the detected language, the engine used, and the number of text blocks found. Provide the image as base64. Use the mode hint (document | receipt | manga | scene) to tune detection.

输入参数langmodeapi_keyqualityimage_base64必填

read_manga

OCR a comic/manga page, routed by LANGUAGE (not the blanket "manga = Japanese" assumption). Japanese goes to the manga specialist reader that reads vertical, hand-lettered speech bubbles in right-to-left order; Korean manhwa, Chinese manhua and other scripts use their own OCR pack; low-confidence pages escalate to the vision model. Returns text blocks in reading order plus the detected language, the engine used, and whether the page is vertical. Provide the image as base64. Pass lang explicitly (ko/zh/...) for the best non-Japanese result; default "auto" detects it.

输入参数langapi_keyimage_base64必填

translate_text

Translate text between 13+ languages with an LLM. Arabic-first quality, with formality control (formal/informal) and optional context to disambiguate meaning. Handles both short dictionary-style word lookups and full documents. Returns the translation and, when available, alternative phrasings.

输入参数text必填api_keycontextformalitytarget_lang必填

ocr_and_translate

One call: OCR an image, then translate every line into target_lang. Arabic-first OCR and manga-aware Japanese with right-to-left-aware layout, followed by LLM translation. Automatic source-language detection. Provide the image as base64. Ideal for reading foreign documents, signs, manga, or receipts end-to-end in a single step.

输入参数api_keytarget_lang必填image_base64必填

get_usage

Check your Auto-Reader OCR key: tier, remaining daily free credits, prepaid credit balance, subscription allowance, and per-minute rate limit. Use it to throttle yourself before hitting a limit.

输入参数api_key

create_api_key

Provision a new Auto-Reader OCR API key instantly, with no human steps. Pass an optional email to unlock the larger free tier (about 250 credits/day, vs about 25/day for an email-less trial key). Store the returned key and pass it as api_key on future calls.

输入参数email

版本历史

1
  1. v1.0.3最新Sep 16, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分