# BrowserHive > Local-first MCP server that gives AI agents isolated, stealthy Chromium sessions, with vault-backed logins the model never sees, human takeover, a full audit trail and an operator dashboard. Documentation for the latest major version (v0, 0.1.3). Install with `bun add -g browserhive`. Every page is also available as Markdown by replacing the trailing slash with `.md`. ## Get started - [Installation](https://browserhive.ai/docs/guide/installation.md): BrowserHive ships as one npm package, browserhive, which provides the browserhive command and a programmatic API. It runs on Bun. You can install it with bun, npm or pnpm, but… - [Quick start](https://browserhive.ai/docs/guide/quick-start.md): This page assumes you have installed BrowserHive and run browserhive init. - [Connecting MCP clients](https://browserhive.ai/docs/guide/mcp-clients.md): BrowserHive speaks MCP over two transports: ## Guides - [Dashboard](https://browserhive.ai/docs/guide/dashboard.md): The dashboard is the operator's view of every agent: what they are doing, what they visited, what they filled from the vault, and what they need from you. Turn it on with… - [Configuration](https://browserhive.ai/docs/guide/configuration.md): Every setting of BrowserHive is a key that you can set in three places: an environment variable, the config file, or a CLI flag. This page explains how they combine. The… - [Security model](https://browserhive.ai/docs/guide/security.md): BrowserHive runs on your machine and treats the agent as untrusted and the operator as trusted. Websites are hostile. This page explains what protects what, and the limits you… - [Vault](https://browserhive.ai/docs/guide/vault.md): The vault lets an agent log in to websites without ever handling the password. The agent names an entry and the form fields; BrowserHive fetches the credential from your… - [Human takeover](https://browserhive.ai/docs/guide/attention.md): Sometimes an agent needs a person: a CAPTCHA, a two-factor prompt, a judgment call. The request_attention tool asks an operator for help and blocks until the operator answers,… - [Stealth](https://browserhive.ai/docs/guide/stealth.md): Stealth makes a BrowserHive session report what a real Chrome on your machine would report, and optionally makes input look hand-made. It is not invisibility. This page says… - [Telemetry](https://browserhive.ai/docs/guide/telemetry.md): Telemetry is off by default, and nothing leaves your machine unless you turn it on. With --otel, BrowserHive exports traces, metrics and logs over OTLP/HTTP to any compatible… - [Command line](https://browserhive.ai/docs/guide/cli.md): If the first argument is not a command word, serve is assumed and every argument is a flag. Each command accepts only its own flags; passing a server flag to purge is a usage… - [Programmatic API](https://browserhive.ai/docs/guide/programmatic-api.md): Embed BrowserHive in your own Bun program, test harness or service with createServer. It uses the same configuration schema and startup sequence as the CLI. - [Upgrading and downgrading](https://browserhive.ai/docs/guide/upgrading.md): BrowserHive follows semantic versioning from 0.1.0. While the major version is 0, breaking changes bump the minor version. Release notes are in the changelog and on GitHub… - [Troubleshooting](https://browserhive.ai/docs/guide/troubleshooting.md): Start with: - [FAQ](https://browserhive.ai/docs/guide/faq.md): Does it run on Node.js? No. Bun ≥ 1.4 is the runtime. You can install the package with npm or pnpm, but Bun must be installed to run it. ## Reference - [Configuration keys](https://browserhive.ai/docs/reference/configuration.md): Every configuration key of BrowserHive (50 keys), generated from the zod schema in @browserhive/contracts/config. For a guided introduction see the configuration guide. - [MCP tools](https://browserhive.ai/docs/reference/tools.md): The 43 tools BrowserHive registers, in registration order, generated from TOOL_CONTRACTS in @browserhive/contracts/tools. Names, parameters, defaults and result shapes are a… - [Errors](https://browserhive.ai/docs/reference/errors.md): Every error code BrowserHive can produce (98 codes), generated from ERROR_REGISTRY in @browserhive/contracts/errors. Each code has a stable anchor: errors.md#, which is… - [REST API](https://browserhive.ai/docs/reference/api.md): The admin REST API served under /api/v1 on the same port as MCP and the dashboard when --admin is on (84 operations), generated from HTTP_ENDPOINTS in… - [WebSocket protocol](https://browserhive.ai/docs/reference/websocket.md): Realtime protocol v1 used by the dashboard for live feeds, the screencast and takeover input. Generated from @browserhive/contracts/ws. Available when --admin is on. ## Optional - [Full documentation in one file](https://browserhive.ai/llms-full.txt) - [Source code](https://github.com/arg1998/BrowserHive) - [npm package](https://www.npmjs.com/package/browserhive)