Koskamo

whoisbrowsing MCP

An official MCP server that allows AI agents to create a whoisbrowsing site, retrieve installation instructions for various platforms, and verify if the tracking script is live on the website without requiring user authentication.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

whoisbrowsing MCP logo, by Sandeep Arneja LLCVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-01Operated by Sandeep Arneja LLC
MCP endpoint (Streamable HTTP)
https://whoisbrowsing.com/mcp
Vendor documentation

What you can do with it

  • Create a new whoisbrowsing site for a domain
  • Get installation instructions for a specific platform
  • Check if the tracking script is connected live

Source and maintenance

Vendor evidenceRegistry 1.0.0

Protocol and capabilities

Server
whoisbrowsing 1.0.0
MCP protocol
2025-06-18
Tools
3 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": true
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

whoisbrowsing shows who is on a website right now: a panel lists every current visitor, and each one's cursor is drawn live on the page they are on when the owner opens it. To add it to a project: 1) create_site with the dev server's host and port (and the production domain if there is one); 2) put the returned snippet on every page, in the file all pages share (get_install_instructions says where for each platform); 3) give the human the watch link, the claim link and the terms sentence right away, and never write either link into a file, commit or log; 4) after a page with the tag is open, check_live with the siteId and the owner key (the part after #wib= in the watch link) says whether the script is connected; never write the key into a file. The full guide: https://whoisbrowsing.com/SKILL.md

Tools

3 advertised

create_site — Create a whoisbrowsing site
Advertised by the server during the last successful anonymous check.

Creates a whoisbrowsing site with no sign-up and returns its script tag (snippet), one watch link per website, a one-time claim link, a terms sentence for the human and the next steps. Call it once per project; one site can hold several domains. Never write the watch or claim link into a file, commit or log.

create_site input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "domains"
  ],
  "properties": {
    "name": {
      "type": "string",
      "maxLength": 100,
      "description": "A label for the site. Defaults to the first domain."
    },
    "domains": {
      "type": "array",
      "items": {
        "type": "string",
        "maxLength": 253
      },
      "maxItems": 20,
      "minItems": 1,
      "description": "The websites the tag will run on: host[:port] (e.g. localhost:3000, example.com), or *.host for every subdomain (e.g. *.example.com). A scheme or path is stripped; a host is letters, digits, hyphens and dots (a non-ASCII domain in its xn-- form); www. is the same website as the bare domain; each website is watched separately."
    }
  }
}
create_site output schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "siteId",
    "snippet",
    "watchUrls",
    "claimUrl",
    "installDocs",
    "terms",
    "next"
  ],
  "properties": {
    "next": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "What to do next, in order, in plain words."
    },
    "terms": {
      "type": "string",
      "description": "A sentence for the human, in the same reply as the two links: opening the watch link or keeping the script is agreeing to the Terms, and confirming they've read the Privacy page."
    },
    "siteId": {
      "type": "string",
      "pattern": "^[a-z0-9]{12}$",
      "description": "The site ID: the data-site value in the snippet. Public, fine to commit."
    },
    "snippet": {
      "type": "string",
      "description": "The script tag to put on every page, unchanged."
    },
    "claimUrl": {
      "type": "string",
      "format": "uri",
      "description": "The one-time link that keeps the site in the human's account after signing in with Google. Expires after 30 days. Give it to the human right away; never write it into a file, commit or log."
    },
    "watchUrls": {
      "type": "object",
      "description": "One watch link per website: the human's own site, opened with a private owner key in the #fragment. Give it to the human right away; never write it into a file, commit or log. Treat it like a password.",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {
        "type": "string",
        "format": "uri"
      }
    },
    "installDocs": {
      "type": "string",
      "format": "uri",
      "description": "Where the tag goes for each platform."
    }
  },
  "additionalProperties": false
}
create_site annotations
{
  "readOnlyHint": false,
  "openWorldHint": false,
  "idempotentHint": false,
  "destructiveHint": false
}
get_install_instructions — Where the tag goes on a platform
Advertised by the server during the last successful anonymous check.
Advertised read-only

Returns the install guide (Markdown) for one platform: where the script tag goes, a Content-Security-Policy note and how to verify. Call it without a platform, or with an unknown one, to get the list of platforms.

get_install_instructions input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "properties": {
    "platform": {
      "type": "string",
      "maxLength": 40,
      "description": "The platform's slug: react, angular, astro, framer, ghost, nextjs, nuxt, html, remix, squarespace, svelte, vue, webflow, wix, ai-agent, wordpress, shopify. Common names such as \"Next.js\" work too."
    }
  }
}
get_install_instructions annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}
check_live — Is the script connected right now?
Advertised by the server during the last successful anonymous check.
Advertised read-only

Asks the live server whether the site's script is connected right now: the websites with a visitor, how many visitors, and which websites the owner is watching. Needs the site's owner key, the part after #wib= in the watch link create_site returned. Load a page that has the tag before calling it: a tab other than the owner view (it shows up as "you, testing"), or a fresh browser context.

check_live input schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "siteId",
    "key"
  ],
  "properties": {
    "key": {
      "type": "string",
      "maxLength": 4096,
      "description": "The owner key: the part after #wib= in the watch link create_site returned. Never write it into a file."
    },
    "siteId": {
      "type": "string",
      "maxLength": 64,
      "description": "The siteId create_site returned (12 lowercase letters and digits)."
    }
  }
}
check_live output schema
{
  "type": "object",
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "required": [
    "siteId",
    "connected",
    "webs",
    "visitors",
    "watching"
  ],
  "properties": {
    "webs": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "siteId": {
      "type": "string"
    },
    "visitors": {
      "type": "integer",
      "maximum": 9007199254740991,
      "minimum": 0
    },
    "watching": {
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "connected": {
      "type": "boolean"
    }
  },
  "additionalProperties": false
}
check_live annotations
{
  "readOnlyHint": true,
  "openWorldHint": false
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
530 ms
95th percentile latency
530 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 530 ms · metadata changed · 3 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http whoisbrowsing-mcp https://whoisbrowsing.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add whoisbrowsing-mcp --url https://whoisbrowsing.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable whoisbrowsing-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "whoisbrowsing-mcp": {
      "url": "https://whoisbrowsing.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "whoisbrowsing-mcp": {
      "type": "streamableHttp",
      "url": "https://whoisbrowsing.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start whoisbrowsing-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "whoisbrowsing-mcp": {
      "type": "http",
      "url": "https://whoisbrowsing.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http whoisbrowsing-mcp https://whoisbrowsing.com/mcp

Claude Desktop

Merge this into claude_desktop_config.json (macOS: ~/Library/Application Support/Claude/, Windows: %APPDATA%\Claude\), then restart Claude Desktop.
Claude Desktop configuration
{
  "mcpServers": {
    "whoisbrowsing-mcp": {
      "url": "https://whoisbrowsing.com/mcp"
    }
  }
}

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "whoisbrowsing-mcp": {
      "serverUrl": "https://whoisbrowsing.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like whoisbrowsing MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Do you run whoisbrowsing MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing