doc-convert-mcp
Document conversion MCP server: PDF to Markdown, image OCR, spreadsheet parsing.
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
~478token 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 0.37%）
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": {
"doc-convert-mcp": {
"url": "https://doc-convert-mcp.onrender.com/mcp/"
}
}
}远程端点
https://doc-convert-mcp.onrender.com/mcp/streamable-http它能做什么
工具清单
工具（4）
🟢 只读🟡 写入🔴 删除⚪ 未知
⚪pdf_to_markdown(pdf_base64, max_pages)
Convert a PDF (base64-encoded bytes) to Markdown, one section per page.
输入模式
{
"type": "object",
"properties": {
"pdf_base64": {
"type": "string",
"description": "The PDF file contents, base64-encoded."
},
"max_pages": {
"default": 100,
"type": "integer",
"description": "Maximum pages to extract (default 100)."
}
},
"required": [
"pdf_base64"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"result": {
"type": "string"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}⚪ocr_image(image_base64, lang)
Run OCR on an image (base64-encoded bytes) and return recognized text.
输入模式
{
"type": "object",
"properties": {
"image_base64": {
"type": "string",
"description": "The image file contents, base64-encoded."
},
"lang": {
"default": "eng",
"type": "string",
"description": "Tesseract language code (default 'eng')."
}
},
"required": [
"image_base64"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"result": {
"type": "string"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}🟢parse_spreadsheet(file_base64, filename)
Parse a CSV or XLSX file (base64-encoded bytes) into Markdown tables.
输入模式
{
"type": "object",
"properties": {
"file_base64": {
"type": "string",
"description": "The spreadsheet file contents, base64-encoded."
},
"filename": {
"type": "string",
"description": "Original filename (used to detect .csv vs .xlsx)."
}
},
"required": [
"file_base64",
"filename"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"result": {
"type": "string"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}🟢url_to_clean_text(url)
Fetch a public http(s) URL and return its main text content as plain text.
输入模式
{
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "The http(s) URL to fetch. Private/loopback hosts are rejected."
}
},
"required": [
"url"
],
"additionalProperties": false
}输出模式
{
"type": "object",
"properties": {
"result": {
"type": "string"
}
},
"required": [
"result"
],
"x-fastmcp-wrap-result": true
}社区
证据
最近观测
已验证未记录版本4 个工具