搜索「OCR」的结果

com.pennyocr/ocr

把 PDF 与图片读成 Markdown 或纯文本，费用明确并设硬性支出上限，每千页 0.75 美元。

com.auto-reader/ocr

以阿拉伯语为主的 OCR、翻译与文档抽取，首次调用即签发免费试用密钥。

OCR 文字识别 —— 图片转文本、多语言

io.smithery.axel-belfort.ocr-extract

面向 AI 智能体的 OCR（光学字符识别）API。通过 URL 或 base64 输入从图片中提取文字，支持置信度评分、语种检测与多语言（英语、法语、德语、西班牙语、中文、日语等）。工具：media_extract_text_from_image。适用于读取文档、票据、截图或任何含文字的图片，是文档处理流水线的必备环节。返回：{text, confidence, language}。无需 API 密钥——在 Base L2 上以 x402 微支付 $0.005/次。

GoCreative 智能体 API 网关

io.smithery.colinhughes2005.gocreative

面向 AI 智能体的按次付费情报服务——无需 API 密钥、无需注册。包含 17 个模型的前沿 LLM 网关（GPT-5、Claude 4.5 Sonnet、Claude Opus 4.6、Gemini 3 Pro、DeepSeek V3.1 等），以及 350 多个数据、合规与增强工具——制裁/KYB 筛查、SEC 文件、加密市场、公司与域名情报、线索调研。智能体通过 x402 协议在 Base 链上以 USDC 按次付费，无需账号、密钥或订阅。亮点：LLM 网关 ai/ask（$0.02）、ai/pro（$0.08）、ai/ultra（$0.25），任选模型以 USDC 支付；KYB-360 在一次调用中整合制裁、PEP、风险、注册信息与公司规模数据；OFAC/EU/UK/UN 及 100 多个名单的制裁筛查；SEC 财务、加密行情、公司与域名情报；共 357 个工具全部按次以 Base 链 USDC 计费。在线 API：https://api.gocreativeai.com，免费模型目录：https://api.gocreativeai.com/v1/ai/models

socrata-mcp-server（政府开放数据）

io.smithery.cyanheads.socrata-mcp-server

检索并查询政府开放数据门户（Socrata SODA API）。

ru.nova-amocrm/amocrm

Remote MCP for amoCRM and Kommo: leads, contacts, tasks, pipelines, chats, Salesbot. OAuth.

io.github.77777R7/octocrawl

Pages, crawls and URL batches as clean Markdown and JSON for AI agents, with an Evidence Record.

io.usefulapi/nocrm-io

Read noCRM.io leads, pipeline steps, comments and client folders; create, update and assign leads.

io.usefulapi/docraptor

Turn HTML or a live URL into polished PDF and Excel files — hosted downloads, async jobs, history.

io.github.theguysaccount/realrep

Read public civic records and World Bank indicators with citations, dates and methodology.

io.github.cyanheads/socrata-mcp-server

检索并查询政府开放数据门户（Socrata SODA API）。

io.github.kriton-dev/pdf-to-markdown

PDF to Markdown and PDF to text from PDF URLs, page by page, with OCR for scanned pages

io.github.kriton-dev/image-to-text

Extract text from images with OCR: plain text plus every line or word with its box

io.github.pipeworx-io/ocrspace

OCR.space MCP——封装 OCR.space API（ocr.space），实现图片/PDF 转文字 OCR。

io.github.mrfentmen/docraptor-mcp

DocRaptor: render HTML to PDF and XLSX documents through the DocRaptor API.

io.github.skavio-eu/processing

Company OAuth PDF, OCR, invoice and audio processing with measured jobs and prepaid company credits.

io.github.zerocrewai/zerocrew-directory

Find the AI agents and tools behind every business job, curated for zero-employee founders.

io.github.sumitrmardy/image-to-text-ocr

OCR text from image URLs, 30 languages, lines with boxes. One flat row per image. Billed on text.

io.github.fastocr-org/fastocr-mcp

OCR scanned PDFs and images into text or searchable PDFs with the FastOCR API.

dev.tanod/apify-image-ocr

Image OCR via Apify. Pay by card with an Apify account, no crypto wallet.

dev.tanod/apify-pdf-ocr

PDF OCR via Apify. Pay by card with an Apify account, no crypto wallet.

io.github.monietools/image-to-text-ocr

Extract text from PNG, JPEG, TIFF, WebP, BMP and GIF images with OCR in 27 languages.

io.github.monietools/pdf-to-text-markdown-ocr

PDF, DOCX and image URLs to clean, LLM-ready Markdown or text, with OCR for scanned pages.

io.github.monietools/monie-tools

Agent tools: clean web screenshots/PDFs, PDF & image OCR to Markdown, PageSpeed audits, email checks