jrodeiro5/media-tools

一个MCP服务器，让你的AI客户端处理PDF、图片、音频、视频和Office文件。 104个工具，一个启动命令。

快速入门 · 工具 · CLI · 发展

---

让你的助理“合并这三个PDF，然后压缩结果”或者“从这段视频剪掉10秒，做个GIF”。它调用匹配工具;文件永远不会离开你的机器。

基于FastMCP构建。支持任何MCP客户端：Claude Desktop、OpenWebUI、Cursor等。

快速开始

指向你的客户端。对于读取mcpServers块的客户端：

设置 PORT 以更改端口。为了只暴露一类工具（并保持客户端上下文较小），运行一个有范围的服务器：media-tools-server-pdf、-image、-audio、-video、-office、-ai 或 -tts。或者在完整服务器上设置 MEDIA_TOOLS_SEARCH=1 只列出 search_tools + call_tool（~330 个令牌，而非 ~13.7k），并让代理通过查询查找工具。

An MCP server that lets your AI client work with PDFs, images, audio, video and Office files. 104 tools, one command to start.

Quick start · Tools · CLI · Development

---

Ask your assistant to “merge these three PDFs, then compress the result” or “cut 10 seconds from this clip and make a GIF”. It calls the matching tools; the files never leave your machine.

Built on FastMCP. Works with any MCP client: Claude Desktop, OpenWebUI, Cursor and others.

Quick start

git clone https://github.com/jrodeiro5/media-tools && cd media-tools
uv sync
uv run media-tools-server        # http://localhost:8020/mcp

Point your client at it. For a client that reads an mcpServers block:

{
  "mcpServers": {
    "media-tools": { "url": "http://localhost:8020/mcp" }
  }
}

Set PORT to change the port. To expose only one family of tools (and keep the client’s context small), run a scoped server: media-tools-server-pdf, -image, -audio, -video, -office, -ai or -tts. Or set MEDIA_TOOLS_SEARCH=1 on the full server to list just search_tools + call_tool (~330 tokens instead of ~13.7k) and let the agent find tools by query.

For a client that shares no disk with the server (an agent in a cluster, behind an MCP gateway), set MEDIA_TOOLS_FILES_IN_CALL=1 together with MEDIA_TOOLS_ROOT: the server adds call_with_files(tool, args, files, outputs), which takes the input files as base64, runs the tool in a temporary folder under the root and returns the files it made as base64.

Tools

PDF · 30merge, split, compress, rotate, reorder, delete pages, watermark, page numbers, protect, unlock, sign, fill forms, compare, redact, returns reclaim, extract text / images / tables / screenshots / structured data, tables to CSV, convert to Markdown, DOCX or PDF/A, images to PDF, Markdown to branded PDF, HTML to PDF, salvage, repair