Skip to main content
Glama

@businessmaps/bifrost

CI npm

MCP server that lets AI tools call functions running in your browser.

The daemon sits between any MCP client and your browser tab. It speaks JSON-RPC over stdio on one side and WebSocket on the other. Your browser app connects, registers tools, and the AI can call them.

Quick start

1. Add to your AI tool

Claude Code:

claude mcp add --transport stdio bifrost -- npx @businessmaps/bifrost --no-auth

Claude Desktop - add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "bifrost": {
      "command": "npx",
      "args": ["@businessmaps/bifrost", "--no-auth"]
    }
  }
}

Cursor - add to .cursor/mcp.json:

{
  "mcpServers": {
    "bifrost": {
      "command": "npx",
      "args": ["@businessmaps/bifrost", "--no-auth"]
    }
  }
}

No install needed. npx downloads and runs the package automatically.

2. Add the client to your browser app

npm i @businessmaps/bifrost-browser

Or via CDN:

<script src="https://unpkg.com/@businessmaps/bifrost-browser"></script>

TypeScript types are included.

3. Register tools

import { BifrostBrowser } from "@businessmaps/bifrost-browser";

const bridge = new BifrostBrowser({ port: 3099 });

bridge.registerTools([
  {
    name: "get_page_title",
    description: "Returns the page title",
    inputSchema: { type: "object", properties: {} },
    handler: async () => document.title,
  },
  {
    name: "get_selection",
    description: "Returns the user's current text selection",
    inputSchema: { type: "object", properties: {} },
    handler: async () => window.getSelection().toString(),
  },
]);

bridge.connect();

That's it. The AI can now call get_page_title and get_selection in your browser tab. Handlers have full access to DOM, Canvas, IndexedDB, Clipboard, fetch, etc.

Related MCP server: @teatak/mcp-server-browser

Auth

By default the daemon generates a random token on startup. Two ways to get it:

  • Terminal mode - the token prints to screen when the daemon starts

  • MCP mode - the AI calls the built-in bifrost_connection_info tool to get the token, then tells you what to paste into your app

Pass the token to the client:

const bridge = new BifrostBrowser({ port: 3099, token: "TOKEN" });

Skip auth entirely with --no-auth during local development.

Multiple tabs

Each tab registers its own tools. Calls route to whoever owns the tool. Disconnecting a tab removes its tools.

Options

--port <port>     WebSocket port        (default: 3099)
--timeout <secs>  Tool call timeout     (default: 120)
--no-auth         Disable token auth    (dev only)
--help, -h        Show this message
--version, -v     Show version

Dev

git clone https://github.com/Business-Maps/bifrost.git && cd bifrost
npm install
npm test

Architecture · Client API · Contributing

License

Apache 2.0

Install Server
A
license - permissive license
-
quality - not tested
D
maintenance

Maintenance

Maintainers
Response time
Release cycle
Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Servers

  • A
    license
    B
    quality
    B
    maintenance
    An MCP server that provides AI models with full browser automation capabilities through Chrome. It enables navigation, interaction, screenshots, and complete DevTools access by bridging AI clients with a companion Chrome extension.
    Last updated
    99
    32
    2
    Apache 2.0
  • A
    license
    -
    quality
    B
    maintenance
    An MCP server that runs in the browser, letting web pages register custom tools and prompts and expose them to an MCP client over WebSocket. Enables agents to drive UI, call page-scoped APIs, and get human-in-the-loop confirmation.
    Last updated
    6
    MIT
  • F
    license
    -
    quality
    D
    maintenance
    Turns your Chrome browser into an MCP server, allowing AI clients to control browser actions like clicking, typing, navigating, and data extraction through custom JavaScript tools.
    Last updated
    29

View all related MCP servers

Related MCP Connectors

  • Live browser debugging for AI assistants — DOM, console, network via MCP.

  • A paid remote MCP for AI agent browser DevTools MCP, built to return verdicts, receipts, usage logs,

  • A paid remote MCP for AI agent browser approval MCP, built to return verdicts, receipts, usage logs,

View all MCP Connectors

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Business-Maps/bifrost'

If you have feedback or need assistance with the MCP directory API, please join our Discord server