Browserbase
Browser automation connector for cloud browser sessions, page fetching, web search, and autonomous browser agents.
Categories: Web Scraping, Data Extraction, Developer Tools
What you can ask
- Read the pricing page at
acme.comand pull out each plan's price and limits. - Search the web for a competitor's latest release notes and summarize what changed.
- Sign in to a vendor portal once, save the session, and reuse that login on every later run.
Set up
Browserbase connects with credentials from your Browserbase account. Have these values ready:
- API key
- Go to Organization > Connectors and find Browserbase.
- Click Enable and choose which tools to allow.
- Each member enters their own values the first time they use it.
To use one account for the whole organization, turn on Share one connection with everyone. Every member's agents then act as that account, with exactly the access it has.
Tools
Browserbase offers 25 tools. Admins choose which ones agents can use. See Tool permission groups.
Read (16)
View and search information without changing it.
| Tool | What it does |
|---|---|
fetch_page | Fetch a URL and return its content, status code, and headers without starting a browser session. |
get_agent | Get a reusable agent by ID, including its system prompt and result schema. |
get_agent_run | Get an agent run by ID — status (RUNNING, COMPLETED, FAILED, STOPPED), its result summary and steps taken, and the failure cause if it did not complete. |
get_context | Get a browser context by ID, including which project owns it and when it was created. |
get_project | Get one Browserbase project by ID, including its concurrency limit and default session timeout. |
get_project_usage | Get browser minutes and proxy bytes consumed by a project this billing period. |
get_session | Get one browser session by ID — status, region, timestamps, and proxy bytes used. |
get_session_live_urls | Get live view and debugger URLs for a RUNNING session, so a person can watch or take over the browser — the way to clear a login or CAPTCHA an automation cannot. |
get_session_logs | Get the Chrome DevTools Protocol log for a session. |
list_agent_runs | List agent runs, newest first, with cursor pagination. |
list_agents | List reusable agents with cursor pagination. |
list_projects | List the Browserbase projects this API key can reach, with each project's concurrency limit and default session timeout. |
list_run_messages | Get the step-by-step message stream for an agent run — what the agent saw, decided, and did. |
list_sessions | List browser sessions, optionally filtered by status (PENDING, RUNNING, COMPLETED, ERROR, TIMED_OUT) or by user metadata via q. |
search_web | Search the web and return structured results with titles and URLs. |
validate_credential | Validate the Browserbase API key with a lightweight call to /v1/projects. |
Write (4)
Create or send data.
| Tool | What it does |
|---|---|
create_agent | Create a reusable agent: a name plus a standing system prompt and result schema that every run started with its agent_id inherits. |
create_context | Create a context that persists cookies and local storage across browser sessions. |
create_session | Start a cloud browser session and return its CDP connect_url for an external automation to drive. |
run_agent | Start an autonomous browser agent on a plain-English task, e.g. 'find the pricing page on example.com and return the cheapest plan'. |
Delete or overwrite (5)
Remove or replace existing data.
| Tool | What it does |
|---|---|
delete_agent | Delete a reusable agent permanently. |
delete_context | Delete a browser context permanently, discarding the cookies and local storage it held. |
release_session | Release a RUNNING browser session so it stops consuming browser minutes and frees a concurrency slot. |
stop_agent_run | Stop a RUNNING agent run before it finishes, ending its browser session. |
update_agent | Update a reusable agent's name, system prompt, or result schema. |