@businessmaps/mcp
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@businessmaps/mcp get the text I have currently selected in the browser"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@businessmaps/bifrost
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-authClaude 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-browserOr 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_infotool 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 versionDev
git clone https://github.com/Business-Maps/bifrost.git && cd bifrost
npm install
npm testArchitecture · Client API · Contributing
License
Apache 2.0
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Maintenance
Related MCP Connectors
The Remote MCP server acts as a standardized bridge between LLM applications (like Claude, ChatGPT, and Cursor) and external services, enabling AI agents to access external tools and resources. Its primary capability is providing a centralized search tool to discover other MCP servers and their respective tools. Unlike local implementations, it runs remotely with OAuth authentication and permission controls for security.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Live browser debugging for AI assistants — DOM, console, network via MCP.
Browz hosted MCP (free public beta): let an AI app drive your own Browz browser profiles from anywhere. Connect https://mcp.gobrowz.com/mcp and sign in with your Browz account (OAuth) or an agent token. Each call is relayed to the Browz app on your computer, which must be online with Remote control on and have a hardware security chip (Mac Secure Enclave or TPM 2.0). 17 tools: profiles, tabs, navigate, snapshot, act, wait, screenshot. No cookies, script, downloads or stored sign-ins remotely.
Related MCP Servers
- AlicenseBqualityDmaintenanceAn 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.9911 npm3Apache 2.0
- AlicenseNot gradedqualityDmaintenanceAn 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.10 npmMIT
- AlicenseNot gradedqualityDmaintenanceTurns 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.28AGPL 3.0
- AlicenseNot gradedqualityDmaintenanceEnables websites to expose JavaScript functions as MCP tools, allowing AI agents to interact with the browser environment via a protocol and Chrome extension.1,110AGPL 3.0