For AI clients

MCP server

An assistant can ask this site directly which tools exist and how to open them, instead of guessing from a search result.

The endpoint

https://bgremover.novusstreamsolutions.com/mcp

One stateless POST, JSON-RPC over HTTP, protocol revision 2026-07-28. There is no account, no key and no sign-up: every tool reads content already public on this site, so an authentication step would be theatre. A GET answers 405 on purpose. That revision removed the server-sent stream, and a client opening one needs a definitive answer rather than a request that hangs.

Adding it to a client

Most clients take a block like this. The server name is yours to choose; the URL is the part that matters.

{
  "mcpServers": {
    "nss-background-remover": {
      "type": "http",
      "url": "https://bgremover.novusstreamsolutions.com/mcp"
    }
  }
}

What it exposes

List every tool on this sitelist_capabilities: Every tool this site offers, with what it accepts, what it produces, and the URL that opens it. Use this to answer "can this site do X?" and to pick the right tool before sending someone to it. These tools run in the visitor's browser, so this server can describe and locate them but cannot execute them.
Find the right tool for a taskfind_tool: Search this site's tools by what someone is trying to do, in their own words: "make a photo transparent", "shrink a video", "read the text in a screenshot". Returns the best matches with the URL that opens each one.
Get the URL and steps to run a toolopen_tool: The URL that opens one tool, plus the steps to operate it. This is the handoff point: this server cannot process a file (everything runs client-side, nothing is uploaded), so the caller (an AI browser, or the person) opens this URL and drives the page. Call list_capabilities or find_tool first to get a slug.
Search the help articles and guidessearch_docs: Search this site's help articles and blog guides. Use it to answer a how-to question, or to cite a page. Returns titles, summaries and URLs.
Read one help articleget_help_article: The full metadata for one help article by slug, with its URL. Use search_docs to find a slug.
List every site in the Novus networklist_novus_sites: The other Novus Stream Solutions sites and what each one is for. Use this when a request is outside what this site does: PDFs, file conversion, study material, music video, AI usage stats, food-market data, or a game. Each site runs its own MCP server at /mcp.

What it will not do

It cannot remove a background, or touch an image at all. Every model here runs inside your own browser tab on a file you chose, and nothing is uploaded, so there is no server-side pipeline for a tool to call. A tool that claimed to process an image would either have to ask for that upload or lie about the result, and the promise that your images never leave the device is architectural here, not a policy.

What it returns instead is which tool fits the job, what it will and will not preserve, and the URL that opens it, so the browser doing the work can be an AI browser or your own. See Privacy for the same guarantee stated for people.