What does this server do that PicGo alone doesn’t?
It provides a standardized MCP tool interface so AI assistants can invoke image uploads through PicGo, enabling automated, in‑context uploading without manual interaction.
@veithly
基本信息
An MCP (Model Context Protocol) server that allows interaction with a running PicGo application to upload images.
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"picgo-ipfs-uploader": {
"command": "npx",
"args": [
"picgo-uploader"
],
"disabled": false,
"alwaysAllow": [
"upload_image_via_picgo"
]
}
}
}Uploads one or more images using the running PicGo server application.
An MCP server that connects to a running PicGo desktop application to upload images. It exposes PicGo’s image uploading capabilities as an MCP tool, allowing AI assistants to upload local image files via PicGo’s built-in server.
Install globally with npm install -g picgo-uploader or yarn global add picgo-uploader, then run the picgo-uploader command. The server listens on stdio and provides the upload_image_via_picgo tool, which accepts an array of absolute image paths.
http://127.0.0.1:36677.It provides a standardized MCP tool interface so AI assistants can invoke image uploads through PicGo, enabling automated, in‑context uploading without manual interaction.
Node.js v18 or later, the PicGo desktop application installed and running, and the PicGo server enabled (default port 36677).
The server does not store images; it relies on PicGo’s configured upload destination (e.g., cloud storage, image host). The URLs returned are provided by PicGo after a successful upload.
The server only supports absolute file paths accessible on the machine where it runs. It cannot handle relative paths or files from other devices.
Transport is stdio. No authentication is required; the server assumes a local, trusted environment where the PicGo server is already accessible.
YC (S26) | Open Computer History | Continuously record your company computer work, map your workflows, help you find work worth automating, and power your agents' context

See and control a real Windows PC you own — from any MCP client, locally or remotely. Observe (UIA + screenshots), click/type/drag/scroll, launch apps, owner Live View. BYOH: your machine, your key.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
Open-source MCP to use Blender with any LLM
评论