You choose how data is processed. Local models run on your device. Cloud models send data to that provider's API.

How much does Vibe Co-Pilot cost?

Vibe is free to install. If you run cloud models, usage is billed by that provider, and paid Vibe plans are optional.

How does Vibe compare to OpenClaw?

OpenClaw is a self-hosted agent stack. Vibe is a browser co-pilot focused on completing overcomplicated web tasks in your existing browser sessions.

How does Vibe compare to Claude Cowork?

Claude browser workflows are Claude-first. Vibe is browser-first and model-flexible, so teams can choose how they run automations.

How does Vibe compare to Chrome DevTools MCP?

DevTools MCP is a browser debugging/control interface. Vibe packages browser task execution into a co-pilot experience for end-to-end workflows.

Can multiple AI agents control the browser at the same time?

Yes. Vibe MCP uses a relay daemon architecture where multiple AI clients (Claude, Cursor, VS Code, etc.) connect via their own stdio MCP bridge to a shared local relay on port 19888, which forwards requests to the Vibe extension on port 19889. Each agent operates independently without conflicts.

Does Vibe Browser MCP require Chrome debug permissions?

No. Vibe Browser MCP uses content scripts and the Chrome Extensions API — no --remote-debugging-port or CDP required. Playwright MCP's extension mode also avoids debug ports, and it can manually attach via --cdp-endpoint if Chrome is already exposing CDP, but its default mode still launches a separate browser. Chrome DevTools MCP requires debug ports. Vibe works with your normal browser profile without any special launch flags.

Can I point my local bridge at a browser on another machine?

Yes, optionally. The same local vibebrowser-mcp bridge can add a --remote flag to dial out to a browser on another machine through the relay, instead of talking to a browser on this machine. It is still a local process. That includes OpenClaw-style remote flows; see the dedicated OpenClaw page for that command-oriented setup.

How does the credential vault work?

The secrets_manager tool lets agents list and read credentials by domain. The typein_secret tool fills form fields directly from the vault — the actual password value is never exposed to the LLM.

Is Vibe Browser MCP open source?

Partially. The npm package (@vibebrowser/mcp) is open source on GitHub and published on npm with the vibebrowser-mcp binary. The Vibe Browser extension itself is not open source.

How do indexed markdown snapshots work?

Instead of sending raw DOM or accessibility tree snapshots, Vibe captures indexed markdown snapshots with interactive elements labeled as [index:score]. Agents use these indices to click, fill, and interact with elements. This drastically reduces token usage and context pollution compared to full page snapshots.

Can Vibe Browser MCP also work as a standalone browser?

Yes. Unlike Browser MCP which is MCP-only, Vibe also functions as a standalone AI co-pilot directly in your browser. Click the extension icon to chat, automate tasks, and get AI assistance — no external agent required.

MCP over stdio · Local process

Run Any AI Agent|'s browser control locally
— no internet relay

vibebrowser-mcp runs as a process next to your agent and talks to the extension over localhost only — the MCP bridge and browser-control path stay on this machine, with no Vibe internet relay involved.

CLI

claude mcp add --transport stdio --scope user vibe -- npx -y -p @vibebrowser/mcp@latest vibebrowser-mcp

Or add to project-level .mcp.json

Requires Node.js and the Vibe Browser extension

Published MCP binary: vibebrowser-mcp. For OpenClaw-style CLI flows, see the separate OpenClaw page.

25+ browser toolsMulti-agent relayRuns on localhost onlyNo debug permissionsOpen source MCP packageFree — no Browserbase account needed

Works with any MCP-compatible agent

C

Claude Code

O

OpenCode

C

Cursor

C

Claude Desktop

V

VS Code

W

Windsurf

G

Gemini CLI

C

Codex

Why run MCP locally

Runs on your machine, not a hosted relay

No bearer credential ever sent over the internet

The safest default when your agent and browser are on the same computer

How the local bridge works

vibebrowser-mcp runs as a child process next to your agent and talks to your browser through a local relay daemon. Multiple agents can share it at once.

Local mode — the default, agents on your machine

npx -y -p @vibebrowser/mcp@latest vibebrowser-mcp

  Claude Code          Cursor           OpenCode
       │                  │                 │
       ▼                  ▼                 ▼
   [vibebrowser-mcp]  [vibebrowser-mcp] [vibebrowser-mcp] ← stdio MCP bridges
       │                  │                 │
       └──────────────────┼─────────────────┘
                          │
                   ws://localhost:19888
                          │
                          ▼
                 ┌──────────────────┐
                 │   Local Relay    │  ← auto-spawned daemon
                 │  (localhost only) │
                 └──────────────────┘
                          │
                   ws://localhost:19889
                          │
                          ▼
                 ┌──────────────────┐
                 │  Vibe Extension  │  ← your real Chrome browser
                 └──────────────────┘

Local setup

1.

Install the Vibe extension and enable AI Agent Control in Settings

Local is the default connection mode — no toggle needed.

2.

Add vibebrowser-mcp to your agent's MCP config

Pick your agent in the reference below — copy, paste, done.

3.

Your agent now talks to your browser over localhost only

Configuration for every agent

Click an agent to see the config. Copy, paste, done.

Local mode defaults to relay port 19888 (no flag needed). The browser extension listens on 19889 — do not point the MCP server at the extension port.

CLI

claude mcp add --transport stdio --scope user vibe -- npx -y -p @vibebrowser/mcp@latest vibebrowser-mcp

Or add to project-level .mcp.json

Need agents outside your machine, or a cloud runner? Hosted remote MCP is on /mcp.

Frequently asked questions

Ready to connect your local AI agent?

Install the extension, add one config block, and start automating — entirely on your machine. Free, with an open source MCP package and browser CLI.

Questions? [email protected] · GitHub · npm · Hosted remote MCP

Personal automation Legal research automation LinkedIn recruiter automation Academic research automation

Run Any AI Agent|'s browser control locally— no internet relay