PennyOCR
🪙 PennyOCR MCP server
원격 Model Context Protocol 서버로서, 모든 에이전트에게 문서를 읽을 수 있는 눈을 제공합니다. URL의 PDF와 이미지를 마크다운(표 보존) 또는 일반 텍스트로 변환하며, 정확한 비용 보고와 하드 지출 상한을 갖추고 있습니다.
https://mcp.pennyocr.com에서 호스팅됩니다 — 설치할 것이 없습니다:
{
"mcpServers": {
"pennyocr": {
"url": "https://mcp.pennyocr.com",
"headers": { "Authorization": "Bearer pk_live_..." }
}
}
}pennyocr.com/dashboard에서 키를 무료로 받을 수 있습니다(월 100페이지). 헤더를 설정할 수 없는 클라인트는 https://mcp.pennyocr.com/?key=pk_live_...를 사용하세요.
도구
도구 | 입력 | 출력 |
|
|
|
|
| 페이지 수 + 정확인 비용 — 무료 |
비용 상한은 어떤 처리보다 먼저 그 숫자와 함께 요청을 거부하므로, 자율 에이전트가 지출("200페이지, $0.15 — 진행")을 사전에 판단할 수 있고, 사전 잔But I need correct "지" collisions etc.
Let's slow down.
Possible major problem: We need ensure there is no hallucinated text. Let's produce now.
Wait, the initial title "PennyOCR MCP server" is exactly. Good.
Let's produce final with no extra spaces. We'll translate the first paragraph as:
"원격 Model Context Protocol 서버로서, 어떤 에이Сентт...
No! Not.
I will write in clean Korean:
"원격 Model Context Protocol 서부터 distance, " "all agents" -> "모든 에이전트"
Let's use standard translation: "a remote Model Context Protocol server that gives any agent document-reading eyes" -> "원격 Model Context Protocol 서버로, 모든 에이전트에 문서 판독 기능을 제공한다." That is okay.
Need maybe "PDF, images by URL" -> "URL로 제공되는 PDF와 이미지" Good.
Full:
원격 [Model Context Protocol](https://modelcontextprotocol.io) 서버로, 어떤 에이전트든 문서를 보을 수 있는 눈을 갖춰 줍니다. URL로 접근하는 PDF/이미지를 마크다운(표 보존prime보존) 또는 일반 텍트스트로 변환하며, **정확한 비용 보局와 견한 지출 한**을 제공합니다.Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Convert PDFs, Office files, spreadsheets and images to clean Markdown, sized for agent context.
Convert PDF, Word, Excel and scanned documents to Markdown, tables and RAG chunks. OCR.
Agent-native document parsing: PDF, scans and FR/EU invoices to structured JSON or Markdown.
PDF, DOCX and image URLs to clean, LLM-ready Markdown or text, with OCR for scanned pages.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceProvides AI agents with comprehensive document parsing capabilities including PDF text extraction, OCR, HTML-to-markdown conversion, table extraction, and summarization, optimized for agent workflows.75 npmMIT
- AlicenseNot gradedqualityDmaintenanceProvides AI agents with document conversion to Markdown, intelligently routing small and large files, and enabling targeted extraction via sections, search, and token budgets.39 PyPI6MIT
- AlicenseAqualityBmaintenanceConverts documents to clean Markdown for AI agents from a URL or base64 — no API key, built for remote hosting. Supports PDF (tables preserved as Markdown/CSV/JSON), DOCX, PPTX, XLSX, EPUB, HTML and CSV; scanned PDFs and images go through offline OCR. Includes full-text search, page-range reading, metadata inspection, PDF split/merge and image export, with SSRF-protected fetching, 30 MB limits and10AGPL 3.0
- AlicenseAqualityCmaintenanceEnables agents to extract multi-page financial tables from complex PDFs, rasterize vector pages into crisp 300 DPI images for vision LLMs, flatten interactive AcroForm/XFA forms, and dewarp skewed OCR bounding boxes from photographed or scanned paper documents. Tool invocations are gated by USDC micropayments settled on Base L2 via the x402 protocol.4MIT