whoisbrowsing

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

Install whoisbrowsing from your coding agent

whoisbrowsing is built so a coding agent (Claude Code, Cursor, Codex and others) can add it to a project with no one signing up first. The agent creates a site, puts one script tag in the right file, and hands you two links: one to watch your visitors live, and one to keep the site under your Google sign-in.

Using an AI coding agent? Give it this prompt:

Add whoisbrowsing (live visitor view) to this project. Follow https://whoisbrowsing.com/SKILL.md exactly.

Copy prompt for your AI agent

By using a script an agent makes for you, you agree to the Terms.

Already have a script?

If you made your script on the whoisbrowsing.com home page, give your agent this prompt with your script in it, so it puts that script in instead of creating a second site:

Add whoisbrowsing (live visitor view) to this project. The site already exists, so skip creating one: put this tag in the file every page shares, and change nothing else:
<paste your script here>
Where it goes for each framework: https://whoisbrowsing.com/SKILL.md

By using a script an agent makes for you, you agree to the Terms.

With the plain prompt, a good agent first looks for a tag already in the project, and asks for yours if you say you have one.

Everything for agents

• SKILL.md One Markdown file with everything an agent needs, from creating the site to verifying it. Also an Agent Skill.
• MCP server Remote, streamable HTTP, no auth: create_site, get_install_instructions and check_live.
• Agent API + OpenAPI POST /api/agent/sites creates a site with no sign-up. The spec is OpenAPI 3.1.
• llms.txt An index of every page and guide as Markdown links, plus llms-full.txt with all of them.
• Markdown twins Add.md to any article, install guide or main page for its Markdown source, like this page's.

MCP server

A remote MCP server over streamable HTTP, with no auth, listed in the official MCP Registry as com.whoisbrowsing/mcp. Add it to your agent once, and it can create the site, read the install guide for your framework and check that the script is connected.

https://whoisbrowsing.com/mcp Copy the URL

• create_site({domains, name?}): creates a site with no sign-up; the same answer as the API: snippet, watch links, claim link.
• get_install_instructions({platform}): where the tag goes on one platform (the install guide's Markdown), or the list of platforms.
• check_live({siteId, key}): whether the script is connected right now: websites, visitors and whether the owner is watching. key is the owner key after #wib= in the watch link.

Claude Code

In your terminal:

claude mcp add --transport http whoisbrowsing https://whoisbrowsing.com/mcp

Syntax from the Claude Code MCP docs.

Cursor

.cursor/mcp.json in the project, or ~/.cursor/mcp.json for every project:

{
  "mcpServers": {
    "whoisbrowsing": {
      "url": "https://whoisbrowsing.com/mcp"
    }
  }
}

Syntax from the Cursor MCP docs.

Codex

In your terminal:

codex mcp add whoisbrowsing --url https://whoisbrowsing.com/mcp

Or in ~/.codex/config.toml:

[mcp_servers.whoisbrowsing]
url = "https://whoisbrowsing.com/mcp"

Syntax from the Codex MCP docs.

Agent API

POST https://whoisbrowsing.com/api/agent/sites creates a site with no sign-up and no auth.

curl -sS -X POST https://whoisbrowsing.com/api/agent/sites \
  -H 'Content-Type: application/json' \
  -d '{"domains":["localhost:3000","example.com"]}'

One site covers localhost and production: list both, and the same tag works on each. Each website gets its own live view, so visitors on localhost never show up on production.

Field	What it is
siteId	The site ID in the tag's data-site. Public.
snippet	The script tag for every page.
watchUrls	One watch link per website. Private: it holds an owner key.
claimUrl	A one-time link to keep the site in your account. Expires after 30 days.
installDocs	Where the tag goes on each platform.
terms	A sentence for you: opening the watch link or keeping the script is agreeing to the Terms.
next	The remaining steps, in plain words.

Errors are JSON with a hint: 400 for a bad body, 429 past the limits (10 sites per network per hour, 5 unclaimed sites per browser). The spec: openapi.json (OpenAPI 3.1). The full walkthrough is SKILL.md.

The two links are for you, not the code

The watch link opens your own site with the live view on. It holds a private owner key, so treat it like a password. The claim link keeps the site in your account once you sign in with Google; it works once and expires after 30 days. A good agent hands you both in its reply and never writes them into the repository. Only the tag goes in the code.

llms.txt and Markdown twins

• llms.txt: an index of every page and guide, as Markdown links.
• llms-full.txt: every guide in one file.
• Markdown twins: add .md to any article, install guide or main page for its Markdown source, for example /install/nextjs.md or /for-agents.md.

Privacy, word for word

• Your visitors' browsers send the page, pointer position, clicks, scroll, device type, source, browser and operating system, and time on site. Never keystrokes, form values or page text.
• Nothing about your visitors is stored on our servers.
• No cookies on your visitors.
• Visitors from the EU/EEA, UK and Switzerland, and browsers with Global Privacy Control, are never shown.

Doing it by hand instead? See install with an AI agent, every install guide, or privacy.

See who is on your website, right now

Type your website, paste one line, and watch your visitors live. No account needed.

Free · Under 4 KB · No cookies on visitors · No visitor data stored