ocr
Read PDFs and images as markdown or text, with exact costs and hard spend caps. $0.75/1k pages.
我该使用它吗
质量与安全性
A
基于对工具定义和协议合规性的自动分析。
上下文开销
~311token 数（工具定义）
~1.1 KB典型响应大小
对注意力的影响极小（占 128k 上下文窗口的 0.24%）
这是每次将服务器的工具加载到模型上下文窗口时所消耗的大致 token 数。数值越高，可用于其他任务的注意力就越少。
安装
一键安装
将以下内容添加到你的 `claude_desktop_config.json` 文件中：
{
"mcpServers": {
"ocr": {
"url": "https://mcp.pennyocr.com"
}
}
}远程端点
https://mcp.pennyocr.comstreamable-http它能做什么
工具清单
工具（2）
🟢 只读🟡 写入🔴 删除⚪ 未知
🟢read_document(url, pages, output, max_pages, max_cost_usd)
Read a document (PDF or image) from a URL and return its contents as markdown (tables preserved) or plain text. Costs $0.00075 per page, billed to the PennyOCR account; the response includes the exact cost_usd and per-page citations. Use estimate_cost first for big documents. Supports page ranges and hard spend caps.
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "http(s) URL of the PDF or image"
},
"pages": {
"type": "string",
"description": "Page range like '1-20,25'. Default: all pages."
},
"output": {
"type": "string",
"enum": [
"markdown",
"text"
],
"description": "Output format. Default markdown."
},
"max_pages": {
"type": "integer",
"description": "Refuse (with the numbers) if selection exceeds this many pages."
},
"max_cost_usd": {
"type": "number",
"description": "Refuse (with the numbers) if the run would cost more than this."
}
},
"required": [
"url"
]
}🟢estimate_cost(url, pages)
Free: return the page count and exact cost_usd to read a document URL with read_document, without running OCR. Use before reading large documents.
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "http(s) URL of the PDF or image"
},
"pages": {
"type": "string",
"description": "Optional page range like '1-20'."
}
},
"required": [
"url"
]
}社区
证据
最近观测
已验证未记录版本2 个工具
已验证未记录版本2 个工具