StackScan MCP server

Ask your assistant what a website runs, and who is behind it.

A Model Context Protocol server for the StackScan Tech Lookup API. Point Claude, Cursor, or any other MCP client at it and you can ask things like:

What is example.com built on?

Who's behind vercel.com? Where are they, what industry, what's their LinkedIn?

How many sites run Klaviyo, and in which countries?

Read-only by design. Nothing here writes to any system of yours.

Install

You need a StackScan account. Sign in, open API Tokens in the dashboard, create a token, and copy your workspace UUID from the same page.

Claude Desktop (extension)

Download stackscan.mcpb from the releases page, then drag it onto Settings > Extensions. It asks for your API token and workspace ID and installs the rest itself.

Claude Desktop (manual config)

Settings → Developer → Edit Config, then add:

{
  "mcpServers": {
    "stackscan": {
      "command": "npx",
      "args": ["-y", "@stackscan/mcp-server"],
      "env": {
        "STACKSCAN_API_TOKEN": "your-token",
        "STACKSCAN_TENANT_ID": "your-workspace-uuid"
      }
    }
  }
}

Restart Claude Desktop. The tools appear under the connectors icon.

Claude Code

claude mcp add stackscan \
  --env STACKSCAN_API_TOKEN=your-token \
  --env STACKSCAN_TENANT_ID=your-workspace-uuid \
  -- npx -y @stackscan/mcp-server

Cursor, Windsurf, and others

Same shape: command: npx, args: ["-y", "@stackscan/mcp-server"], and the two environment variables. Check your client's own MCP docs for where its config file lives.

Tools

A lookup that finds nothing is not charged. Neither is check_credits.

Breadth vs depth

There are two technology tools and they answer different questions. lookup_domains_technologies is the breadth view: many domains, technology names only, ideal for "which of these run Shopify?". lookup_domain_technologies is the depth view: one domain, every technology with its category and how many sites use it globally. The batch tool reports how many technologies it left out per domain, so the model can offer to drill in.

Why the batch tools stop at 20

The REST endpoints behind them take 100 domains per request, and these tools deliberately do not. A tool result goes straight into the model's context, and a hundred full company payloads is tens of thousands of tokens, which crowds out the conversation you are actually having, and the model then has to re-read all of it to answer anything. Twenty compact rows is a table a model can reason over.

It also refuses rather than truncates. If a batch would cost more than your session cap allows, it charges nothing and tells you how many you can afford. Quietly dropping domains would hand back an answer that looks complete and is not.

If you genuinely need hundreds of domains, that is what the REST endpoint is for.

Configuration

... View full README on GitHub