ImgVX AI

npx add-mcp 'https://imgvx.com/mcp'

ImgVX AI MCP server

Connect ImgVX AI to Claude, ChatGPT, Cursor, VS Code or any other app that speaks the Model Context Protocol (MCP). Ask your assistant to remove a background, upscale a photo or compress an image to 100 KB, and it answers with the right free ImgVX AI tool and a link to open it.

Server URL	https://imgvx.com/mcp
Transport	Streamable HTTP
Authentication	None: no sign-in, no API key
Tools	3, all read-only

What it does

• find_image_tool: give it a job in plain words (“make this logo transparent”, “photo is too blurry”, “HEIC to JPG”) and it returns the matching tools, what each does, what it costs (almost always nothing) and a link. With a language such as es or ja the link goes to the page in that language where one exists.
• list_image_tools: every tool, or one category, with a link to each.
• get_pricing: what is free and what Pro and the credit packs cost.

The server never sees an image. ImgVX AI edits photos inside the user’s own browser, so the assistant’s job is to send the user to the right tool; the photo stays on their device.

Claude

In Claude (web or desktop), open Settings → Connectors → Add custom connector, name it ImgVX AI and paste https://imgvx.com/mcp. In Claude Code:

claude mcp add --transport http imgvx-ai https://imgvx.com/mcp

ChatGPT

With developer mode on (Settings → Apps & Connectors → Advanced), choose Create, name it ImgVX AI, paste https://imgvx.com/mcp and pick No authentication.

Cursor

// ~/.cursor/mcp.json
{
  "mcpServers": {
    "imgvx-ai": { "url": "https://imgvx.com/mcp" }
  }
}

VS Code (GitHub Copilot)

// .vscode/mcp.json
{
  "servers": {
    "imgvx-ai": { "type": "http", "url": "https://imgvx.com/mcp" }
  }
}

Windsurf

// ~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "imgvx-ai": { "serverUrl": "https://imgvx.com/mcp" }
  }
}

Zapier, Make and n8n

Add an MCP client step (Zapier MCP Client, Make MCP Client, n8n MCP Client Tool on an AI Agent node), set the URL to https://imgvx.com/mcp, transport Streamable HTTP, and no authentication.

Try it by hand

curl -s https://imgvx.com/mcp -H "Content-Type: application/json" -d '{"jsonrpc":"2.0","id":1,"method":"tools/call","params":{"name":"find_image_tool","arguments":{"task":"remove background"}}}'

For AI assistants

A plain-text summary of the site is at /llms.txt, and every tool is listed in /llms-full.txt.

Questions or a client that does not connect: [email protected].