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.

How is Vibe Browser MCP different from Playwright MCP, Chrome DevTools MCP, and BrowserMCP?

Playwright MCP and Chrome DevTools MCP launch a separate browser by default. Playwright MCP can connect to your existing browser either through its Chrome extension mode or through an explicit --cdp-endpoint when Chrome remote debugging is already enabled, but that is still manual setup and it still lacks multi-agent support, Google Workspace tools, credential vault, and sub-agent orchestration. Chrome DevTools MCP requires --remote-debugging-port and sends telemetry to Google. BrowserMCP is a Chrome extension like Vibe but only supports a single agent, has ~13 tools, and its extension is closed-source. Vibe Browser MCP supports multiple agents simultaneously, offers 25+ tools, includes Google Workspace integration, a credential vault, sub-agent orchestration, and uses indexed markdown snapshots for lower token usage.

I don't want my browser traffic to touch the internet — what should I use instead?

Use local stdio MCP — it runs as a process on your machine and never sends browser-control traffic over the internet. See vibebrowser.app/mcp-stdio.

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

Yes. Each agent sends its own X-Remote-Session header value to the hosted endpoint independently — there's no local daemon or port to share, so multiple direct HTTP clients (or a mix of direct HTTP and local stdio agents) can drive the browser without conflicting.

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.

What AI agents work with Vibe Browser MCP over the hosted remote endpoint?

Any MCP client that supports the Streamable HTTP transport. Verified remote configs are published for Claude Code, Codex CLI, GitHub Copilot (VS Code and CLI), Cursor, and OpenCode, plus a generic JSON contract for any other Streamable HTTP client.

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.

Why does it matter that Vibe uses my real browser?

Playwright MCP and Chrome DevTools MCP launch a fresh, separate browser by default with no sessions, cookies, or extensions. Vibe Browser MCP connects directly to the browser you are already using with zero configuration, so agents can interact with Gmail, Slack, GitHub, Jira, or any logged-in site without re-authenticating.

Hosted · Streamable HTTP

Give Claude Code|
a real browser — from anywhere

Your real logged-in browser, exposed as a hosted MCP endpoint. No local process, no port forwarding, no VPN.

25+ browser toolsMulti-agent, no local daemonHosted Streamable HTTP relayNo debug permissionsOpen source MCP packageFree — no Browserbase account needed

Don't want browser-control traffic to touch the internet? Run Vibe MCP locally instead — the MCP bridge and browser-control path stay on your machine, with no Vibe internet relay involved. See the local stdio setup.

One endpoint, one header

Every remote client — CLI, IDE, or cloud runner — talks to the same hosted endpoint with the same header.

Endpoint

https://relay.api.vibebrowser.app/mcp

Header

X-Remote-Session

Value

The UUID from Settings → AI Agent Control → Remote (internet) → Relay access.

The bare UUID is the primary, shortest form. The canonical wss://relay.api.vibebrowser.app/YOUR-SESSION-UUID URL shown by the same extension control is also an accepted header value — use whichever string the extension hands you.

Configuration for every agent

Click an agent to see its config. Copy, paste, add your UUID, done.

No built-in MCP

Pi

No built-in MCP by design — custom/third-party extension only.

Pi has no built-in MCP support by design — only a custom or third-party Pi extension could add it. Vibe also works as a standalone in-browser co-pilot — no MCP required.

.mcp.json (or ~/.claude.json)

{
  "mcpServers": {
    "vibebrowser": {
      "type": "http",
      "url": "https://relay.api.vibebrowser.app/mcp",
      "headers": {
        "X-Remote-Session": "${VIBE_REMOTE_UUID}"
      }
    }
  }
}

Claude Code expands ${VAR} inside .mcp.json's headers field for HTTP servers — set VIBE_REMOTE_UUID in your shell, never hardcode the UUID in a committed file. Or run: claude mcp add --transport http --scope user vibebrowser https://relay.api.vibebrowser.app/mcp --header "X-Remote-Session: <uuid>"

Handle your relay credential safely. Your X-Remote-Session value is a bearer credential for your real, logged-in browser — anyone who holds it can drive it. Keep it out of shared chat logs, screenshots, and public repos, and never commit it to a config file. Prefer to keep this credential off the internet entirely? See the local stdio setup instead.

Capability surfaces

What agents can actually do through Vibe Browser MCP

Package the browser, workspace, security, and coordination layers as explicit surfaces. That is the useful lesson from infrastructure products like Tavily, translated to a real-browser MCP.

Browser control

Drive the live browser session your operator already trusts

Open tabs, navigate, click, fill, drag, type, and scroll inside the same logged-in browser profile instead of a disposable automation runtime.

Why teams reach for this surface

This is the right surface when your agent needs real UI state, installed extensions, existing cookies, and human-visible execution.

Works on authenticated SaaS, portals, and internal tools

Keeps the human in the same browser context as the agent

Avoids extra browser launch flags or CDP ceremony

Representative tools

navigate_pageclickfill_formpress_keydrag

Packaging that technical buyers understand

Tavily makes its product legible by naming a small set of surfaces clearly. The equivalent move for Vibe is not “search” or “crawl”; it is browser control, snapshots, workspace actions, secrets, and agent coordination.

Proof points already present in this route

25+

published tools across browser, workspace, security, and agent orchestration

Local + remote

relay paths for laptop agents and internet-reachable runners

Multi-agent

one real browser session can be shared by multiple cooperating agents

Real sessions

cookies, tabs, extensions, and authenticated apps stay intact

25+ tools across 8 categories

Navigation, interaction, Google Workspace, credential management, skills, sub-agents, and more — all exposed via MCP.

Navigation

2

navigate_pageNavigate to a URL or go back / forward / reload

wait_forWait for text to appear on the page

Tab Management

3

list_pagesList open browser pages/tabs

new_pageOpen a new page with optional URL

close_pageClose a page by ID

Index-Based Interaction

5

clickClick by canonical ref like A7, M12, or 12

fillFill an input/select/contenteditable by canonical ref

fill_formFill multiple fields in one call

scroll_pageScroll page up or down

media_controlControl video/audio playback

Advanced Interaction

4

type_textType into the focused field

press_keySend keyboard keys and shortcuts

hoverHover to trigger tooltips/menus

dragDrag between elements or coordinates

Utility

4

waitWait N seconds

subagentSpawn sub-agent with isolated context

parallelExecute multiple tools in parallel

web_fetchHTTP fetch + text extraction

Inspection & State

6

take_snapshotTake indexed page snapshot (`type='markdown'` default or `type='a11y'`)

take_html_snapshotTake a dedicated indexed HTML snapshot

take_screenshotJPEG screenshot with resize, grayscale, quality controls

evaluate_scriptRun JavaScript in the current page context

list_network_requestsList captured network requests

get_network_requestInspect one captured request/response

Google Workspace

8

gmail_searchSearch emails via Gmail API

gmail_get_messageGet full email content

gmail_get_threadGet all messages in thread

gmail_create_draftCreate email draft

gmail_send_messageSend email

calendar_viewView upcoming events

calendar_createCreate calendar event

calendar_deleteDelete a calendar event

Credential Management

5

secrets_managerList/read saved credentials

typein_secretFill form from vault (hidden from LLM)

settingsRead or update extension settings and skills

settings_listList stored settings keys and skill entries

memory_searchRecall stored context before acting

Skills Library

Turn workflows into reusable skills and share them across agents or teams.

Secrets Vault + Type-In

Internal password vault with a fill tool that never exposes secrets to the LLM.

Model & Agent Choice

Works with Vibe AI, Anthropic Claude Max, GitHub Copilot, and BYOK providers.

How Vibe Browser MCP compares

Vibe Browser MCP is the only browser MCP that uses your real browser with all your logged-in sessions — no debug ports, no separate browser instance.

Feature	Vibe Browser MCP	Playwright MCP	DevTools MCP	Browser MCP
Uses your logged-in browser Playwright supports this via its extension mode, but defaults to launching a separate browser instance
No debug port required Playwright's default mode requires --remote-debugging-port; extension mode avoids this but adds token auth setup
Multi-agent support Multiple AI agents control the same browser simultaneously — via the local relay daemon (stdio) or independent hosted HTTP sessions (remote)
Internet-exposed relay Reach your browser over the internet — via the hosted Direct HTTP endpoint on this page, or an optional relay-exposed stdio bridge on /mcp-stdio
Google Workspace integration Gmail search/send/draft/thread/message plus Calendar view/create/delete — 8 native tools
Credential vault Secure password manager that never exposes secrets to the LLM
Sub-agent orchestration Spawn sub-agents with isolated context and parallel tool execution
Standalone AI browser Also works as a standalone AI co-pilot directly in your browser
Open source Vibe's npm package (@vibebrowser/mcp) ships the vibebrowser-mcp binary as open source; the browser extension is not. BrowserMCP is similar
Telemetry to vendor Chrome DevTools MCP sends usage statistics and CrUX API calls to Google by default

Playwright MCP (Microsoft)

Launches a separate Playwright-managed browser. Requires CDP for existing browser connection. 27k GitHub stars.

Chrome DevTools MCP (Google)

Developer debugging tool using Puppeteer + CDP. Launches separate Chrome instance. Sends telemetry to Google by default. 25k GitHub stars.

Browser MCP (Namu)

Chrome extension-based like Vibe. Single agent only. Extension is closed-source. 5.8k GitHub stars.

Frequently asked questions

Ready to connect your AI agent from anywhere?

Grab your relay UUID from the extension, add one config block, and go. Prefer to stay fully local? Use local stdio MCP instead.

Questions? info@vibebrowser.app · GitHub · npm · Local stdio setup

Personal automation Legal research automation LinkedIn recruiter automation Academic research automation

Give Claude Code|
a real browser — from anywhere

One endpoint, one header

Configuration for every agent

Claude Code

Codex CLI

GitHub Copilot (VS Code)

GitHub Copilot CLI

Cursor

OpenCode

Generic MCP client

Pi

What agents can actually do through Vibe Browser MCP

Drive the live browser session your operator already trusts

25+ tools across 8 categories

Navigation

Tab Management

Index-Based Interaction

Advanced Interaction

Utility

Inspection & State

Google Workspace

Credential Management

Skills Library

Secrets Vault + Type-In

Model & Agent Choice

How Vibe Browser MCP compares

Playwright MCP (Microsoft)

Chrome DevTools MCP (Google)

Browser MCP (Namu)

Frequently asked questions

Ready to connect your AI agent from anywhere?

Give Claude Code|a real browser — from anywhere

One endpoint, one header

Configuration for every agent

Claude Code

Codex CLI

GitHub Copilot (VS Code)

GitHub Copilot CLI

Cursor

OpenCode

Generic MCP client

Pi

What agents can actually do through Vibe Browser MCP

Drive the live browser session your operator already trusts

25+ tools across 8 categories

Navigation

Tab Management

Index-Based Interaction

Advanced Interaction

Utility

Inspection & State

Google Workspace

Credential Management

Skills Library

Secrets Vault + Type-In

Model & Agent Choice

How Vibe Browser MCP compares

Playwright MCP (Microsoft)

Chrome DevTools MCP (Google)

Browser MCP (Namu)

Frequently asked questions

How is Vibe Browser MCP different from Playwright MCP, Chrome DevTools MCP, and BrowserMCP?

I don't want my browser traffic to touch the internet — what should I use instead?

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

Does Vibe Browser MCP require Chrome debug permissions?

What AI agents work with Vibe Browser MCP?

How does the credential vault work?

Is Vibe Browser MCP open source?

What are indexed markdown snapshots?

Can Vibe Browser MCP also work as a standalone browser?

Why does it matter that Vibe uses my real browser?

Ready to connect your AI agent from anywhere?

Give Claude Code|
a real browser — from anywhere