converter
Convert files between 44 formats: documents, spreadsheets, images, ebooks, email and subtitles.
我该使用它吗
质量与安全性
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": {
"converter": {
"url": "https://filetypeconverters.com/api/mcp"
}
}
}远程端点
https://filetypeconverters.com/api/mcpstreamable-http它能做什么
工具清单
工具（5）
🟢list_formats
List every file format this converter reads or writes (id, name, extensions, family). Use the id values as `from`/`to` in other tools.
输入模式
{
"type": "object",
"properties": {},
"additionalProperties": false
}🟢check_conversion(from, to)
Check whether one format can be converted to another before sending a file. Returns the engine, whether AI Deep Read is needed, the options it accepts, and alternatives when the pair is not supported. Formats accept ids (docx), extensions (jpeg) or common names (word, excel).
输入模式
{
"type": "object",
"properties": {
"from": {
"type": "string",
"description": "Source format, e.g. pdf"
},
"to": {
"type": "string",
"description": "Target format, e.g. docx"
}
},
"required": [
"from",
"to"
],
"additionalProperties": false
}🟢list_conversions(from, to)
List supported target formats for a source format (or every source that can produce a target). Returns compact {from,to,slug,engine,mode} rows.
输入模式
{
"type": "object",
"properties": {
"from": {
"type": "string"
},
"to": {
"type": "string"
}
},
"additionalProperties": false
}🟡convert_file(filename, base64, url, from, to, ...)
Convert a file. Provide the content as base64 OR a public https URL. `from` is optional when the filename/URL has an extension. Text outputs (Markdown, CSV, JSON, HTML…) up to 200 KB are returned inline as `text`; other outputs are returned as `base64` plus a `downloadUrl` that accepts the same bearer token. Max 10 MB per file. Set `deepRead: true` to read scans, photos and handwriting with AI Deep Read (1 credit per page).
输入模式
{
"type": "object",
"properties": {
"filename": {
"type": "string",
"description": "Original filename with extension, e.g. report.pdf"
},
"base64": {
"type": "string",
"description": "File bytes, base64-encoded"
},
"url": {
"type": "string",
"description": "Public https URL of the file (alternative to base64)"
},
"from": {
"type": "string",
"description": "Source format id; detected from the filename when omitted"
},
"to": {
"type": "string",
"description": "Target format id, e.g. md, docx, xlsx, png"
},
"options": {
"type": "object",
"description": "Engine options from check_conversion (delimiter, sheet, quality, …)"
},
"deepRead": {
"type": "boolean",
"description": "Use AI Deep Read (OCR + layout understanding) for PDFs and images"
}
},
"required": [
"to"
],
"additionalProperties": false
}🟢get_conversion(id)
Fetch a previous conversion by id: status, warnings, and the output (inline text or base64) if it is still retained.
输入模式
{
"type": "object",
"properties": {
"id": {
"type": "string"
}
},
"required": [
"id"
],
"additionalProperties": false
}社区
证据