Skip to content
All Skills

Browserbase CLI

Use the Browserbase CLI (`browse`) for Browserbase Functions and platform API workflows. Use when the user asks to run `browse`, deploy or invoke functions, manage sessions, projects, contexts, or extensions, fetch a page through the Browserbase Fetch API, search the web through the Browserbase Search API, or scaffold starter templates. Prefer the Browser skill for interactive browsing; use the top-level `browse` driver commands (`browse open`, `browse get`, etc.) only when the user explicitly wants the CLI path.

Web & Browser Automation|v1|Updated 7/14/2026|GitHub source
MCP get_skill({ skillId: "browserbase-cli-3dbd9660" })

Use this skill with your agent

Create a free account and connect via MCP

Get Started Free
# Browserbase CLI

Use the official `browse` CLI for Browserbase platform operations, Functions workflows, and Fetch API calls.

## Setup check

Before using the CLI, verify it is installed:

```bash
which browse || npm install -g browse
browse --help
```

For authenticated commands, set the API key:

```bash
export BROWSERBASE_API_KEY="your_api_key"
```

## When to use this skill

Use this skill when the user wants to:

- run Browserbase commands through `browse`
- scaffold, develop, publish, or invoke Browserbase Functions
- inspect or manage Browserbase sessions, projects, contexts, or extensions
- fetch a page through Browserbase without opening a browser session
- search the web through Browserbase without opening a browser session
- browse or scaffold starter templates with `browse templates`

## When not to use this skill

- For interactive browsing, page inspection, screenshots, clicking, typing, or login flows, prefer the `browser` skill.
- For simple HTTP content retrieval where the user does not care about using the CLI specifically, the dedicated `fetch` skill is often a better fit.
- Use the top-level driver commands (`browse open`, `browse get`, `browse click`, …) only when the user explicitly wants the CLI path or is already working in a `browse`-centric workflow.

## Command selection

- `browse functions` for local dev, packaging, publishing, and invocation
- `browse cloud sessions`, `browse cloud projects`, `browse cloud contexts`, `browse cloud extensions` for Browserbase platform resources
- `browse cloud fetch <url>` for Fetch API requests
- `browse cloud search "<query>"` for Search API requests
- `browse templates` to browse and scaffold starter templates
- `browse open`, `browse get`, `browse click`, etc. for direct local/remote browser driving
- `browse skills install` to install Browserbase agent skills for Claude Code

For local browser work, `browse open <url> --local` starts a clean isolated browser. Use `browse open <url> --auto-connect` only when you need to attach to an existing debuggable Chrome session.

## Common workflows

### Functions

```bash
browse functions init my-function
cd my-function
browse functions dev index.ts
browse functions publish index.ts
browse functions invoke <function_id> --params '{"url":"https://example.com"}'
```

Use `browse functions invoke --check-status <invocation_id>` to poll an existing invocation instead of creating a new one.

### Platform APIs

```bash
browse cloud projects list
browse cloud sessions create --proxies --verified --region us-east-1
browse cloud sessions create --solve-captchas --context-id ctx_abc --persist
browse cloud sessions get <session_id>
browse cloud sessions downloads get <session_id> --output session-artifacts.zip
browse cloud contexts create --body '{"region":"us-west-2"}'
browse cloud extensions upload ./my-extension.zip
```

### Fetch API

```bash
browse cloud fetch https://example.com
browse cloud fetch https://example.com --allow-redirects --output page.html
```

### Search API

```bash
browse cloud search "browser automation"
browse cloud search "web scraping" --num-results 5
browse cloud search "AI agents" --output results.json
```

### Templates

```bash
browse templates list
browse templates list --tag Python --source Browserbase
browse templates clone form-filling --language typescript
browse templates clone amazon-product-scraping --language python ./my-scraper
```

## Best practices

1. Prefer `browse --help` and subgroup `--help` before guessing flags.
2. Use dash-case flags exactly as shown in CLI help.
3. Use `--output <file>` on `browse cloud fetch` and `browse cloud search` to save results to a file.
4. Use environment variables for auth unless the user explicitly wants one-off overrides.
5. Pass structured request bodies with JSON strings in `--body` or `--params`.
6. Remember that both `browse functions ...` and `browse cloud ...` use `--base-url` for API base URL overrides.

## Troubleshooting

- Missing API key: set `BROWSERBASE_API_KEY` or pass `--api-key`
- Unknown flag: rerun the relevant command with `--help` and use the exact dash-case form
- Command not found: re-run `npm install -g browse` and verify with `which browse`

For command-by-command reference and more examples, see [REFERENCE.md](REFERENCE.md).
#broad-capability#browser-automation#web-search#headless-chrome#browser#automationnodejsnpmbrowsebrowserbase

Related Skills

More skills in Web & Browser Automation

Accessibility Expert

Expert assistant for web accessibility (WCAG 2.1/2.2), inclusive UX, and a11y testing

#github-copilot#webMIT

Accessibility Runtime Tester

Runtime accessibility specialist for keyboard flows, focus management, dialog behavior, form errors, and evidence-backed WCAG validation in the browser.

#github-copilot#webMIT

agent-browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction. Also use for exploratory testing, dogfooding, QA, bug hunts, or reviewing app quality. Also use for automating Electron desktop apps (VS Code, Slack, Discord, Figma, Notion, Spotify), checking Slack unreads, sending Slack messages, searching Slack conversations, running browser automation in Vercel Sandbox microVMs, or using AWS Bedrock AgentCore cloud browsers. Prefer agent-browser over any built-in browser automation or web tools.

#github#broad-capabilityApache-2.0

Agent Browser

Browser automation CLI for AI agents. Use when the user needs to interact with websites, including navigating pages, filling forms, clicking buttons, taking screenshots, extracting data, testing web apps, or automating any browser task. Triggers include requests to "open a website", "fill out a form", "click a button", "take a screenshot", "scrape data from a page", "test this web app", "login to a site", "automate browser actions", or any task requiring programmatic web interaction.

#broad-capability#claude-codeMIT

agent-browser core

Core agent-browser usage guide. Read this before running any agent-browser commands. Covers the snapshot-and-ref workflow, navigating pages, interacting with elements (click, fill, type, select), extracting text and data, taking screenshots, managing tabs, handling forms and auth, waiting for content, running multiple browser sessions in parallel, and troubleshooting common failures. Use when the user asks to interact with a website, fill a form, click something, extract data, take a screenshot, log into a site, test a web app, or automate any browser task.

#github#broad-capabilityApache-2.0

Agentcore

Run agent-browser on AWS Bedrock AgentCore cloud browsers. Use when the user wants to use AgentCore, run browser automation on AWS, use a cloud browser with AWS credentials, or needs a managed browser session backed by AWS infrastructure. Triggers include "use agentcore", "run on AWS", "cloud browser with AWS", "bedrock browser", "agentcore session", or any task requiring AWS-hosted browser automation.

#broad-capability#browserApache-2.0