Faceabot PDF text extractor
Read the text of any public PDF, page by page, plus page count and metadata. Free, no key.
我该使用它吗
质量与安全性
发现（3）
- HIGHTool poisoning patterns detected
- MEDIUMTool description contains URL to non-standard domain在 pdf_extract_text 中
- MEDIUMTool description contains URL to non-standard domain在 pdf_info 中
基于对工具定义和协议合规性的自动分析。
上下文开销
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": {
"pdf": {
"url": "https://pdf.faceabot.com/mcp"
}
}
}远程端点
https://pdf.faceabot.com/mcpstreamable-http它能做什么
工具清单
工具（2）
🟢pdf_extract_text(url, pages, start, max_chars)
Reads a PDF from its public https address and returns its text, page by page (parse / read a PDF: invoices, papers, reports, contracts, forms…). Up to 10 MB; use start to read further. Use when: you need the text content of a PDF file. Not for scanned PDFs (images only): those need OCR. Example: {"url":"https://pdf.faceabot.com/sample.pdf"}
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public https address of the PDF file",
"examples": [
"https://pdf.faceabot.com/sample.pdf"
]
},
"pages": {
"type": "string",
"description": "Optional pages to read, e.g. \"1-3\" or \"2,5\". Default: all"
},
"start": {
"type": "integer",
"minimum": 0,
"default": 0,
"description": "Character offset to continue a long text"
},
"max_chars": {
"type": "integer",
"minimum": 500,
"maximum": 50000,
"default": 20000
}
},
"required": [
"url"
],
"additionalProperties": false
}🟢pdf_info(url)
Number of pages, title, author, creation date and whether the PDF has extractable text. Use when: you want to know what a PDF is before reading it. Example: {"url":"https://pdf.faceabot.com/sample.pdf"}
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"format": "uri",
"description": "Public https address of the PDF file",
"examples": [
"https://pdf.faceabot.com/sample.pdf"
]
}
},
"required": [
"url"
],
"additionalProperties": false
}社区
证据