WallScout in your AI assistant

Set it up in two minutes

Every assistant needs the same thing: the server URL below. The first time it calls WallScout, it opens a WallScout sign-in page. Sign in, check which app is asking, and click Allow access. Some apps, like Cursor, then leave your browser on a localhost page that can’t load. That’s normal: the app is already connected, so you can close the tab.

https://app.wallscout.io/api/mcp

Menu names move around between versions and plans, so if a step looks different, look for “connectors” or “MCP” in the settings.

Claude (web, desktop and mobile)

1. Open Settings → Connectors and choose Add custom connector. On a Team or Enterprise plan, an owner adds it once in the organization settings.
2. Name it WallScout, paste the URL and add it.
3. Click Connect, sign in to WallScout and allow access. A connector you add on the web is available in the Claude apps too.

ChatGPT

1. Open Settings → Apps & Connectors. Depending on your plan, custom connectors may need developer mode (under Advanced settings) or an admin on Business plans.
2. Create a connector named WallScout with the URL above and OAuth as the authentication.
3. Sign in to WallScout, allow access, then pick WallScout from the tools menu in a new chat.

Claude Code

claude mcp add --transport http wallscout https://app.wallscout.io/api/mcp

Then run /mcp inside Claude Code and choose Authenticate next to wallscout.

Cursor

Add this to ~/.cursor/mcp.json (or the project’s .cursor/mcp.json), then connect it from Cursor’s MCP settings:

{
  "mcpServers": {
    "wallscout": { "url": "https://app.wallscout.io/api/mcp" }
  }
}

VS Code

Add this to .vscode/mcp.json, then start the server from the editor and sign in when asked:

{
  "servers": {
    "wallscout": { "type": "http", "url": "https://app.wallscout.io/api/mcp" }
  }
}

Other assistants

Any client that supports remote MCP servers (Streamable HTTP) with OAuth works with the URL above. For a client that can only start local servers, use the open-source mcp-remote bridge:

npx -y mcp-remote https://app.wallscout.io/api/mcp

The tools your assistant gets

Your assistant picks the right tool on its own. Here is what each one does and what it uses from your plan.

Two ready-made prompts come with it: Should I sell this product? and Review my watchlist. Assistants that support MCP prompts list them in their prompt or slash menu; anywhere else, just ask in your own words.

Same account, same numbers, same quota

The assistant works on your WallScout account. An analysis it runs shows up in your history in the web app, counts against your plan like any other, and returns the same estimate you would see on the result page, along with a link to open it there. AI assistants come with the Pro plan, along with everything else in it.

Monthly estimates come from a product’s weekly sales history; bulk results show one recent week. If a product has too little history, WallScout says the demand is unknown rather than zero.

Security and privacy

• Standard OAuth sign-in. You approve each assistant on a WallScout page that shows which app is asking and where you’ll be sent back. Assistants never see your password.
• Disconnect any time. Account → AI assistants lists every connected app. Disconnecting cuts its access to your data straight away.
• Nothing beyond your own account. An assistant can’t see your payment details or change your plan.
• What we keep. Analyses are saved to your history as usual. For each tool call we record which tool ran and whether it worked, not your conversation. Your chats stay with your AI provider, under their privacy policy.