Browserbase MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| GEMINI_API_KEY | Yes | Your Gemini API key (required when using the default Gemini model) | |
| BROWSERBASE_API_KEY | Yes | Your Browserbase API key | |
| BROWSERBASE_PROJECT_ID | Yes | Your Browserbase project ID |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browserbase_session_createC | Create or reuse a Browserbase browser session and set it as active. |
| browserbase_session_closeA | Close the current Browserbase session and reset the active context. |
| browserbase_stagehand_navigateA | Navigate to a URL in the browser. Only use this tool with URLs you're confident will work and be up to date. Otherwise, use https://google.com as the starting point |
| browserbase_stagehand_actB | Perform a single action on the page (e.g., click, type). |
| browserbase_stagehand_extractC | Extract structured data or text from the current page using an instruction. |
| browserbase_stagehand_observeB | Find interactive elements on the page from an instruction; optionally return an action. |
| browserbase_screenshotC | Capture a full-page screenshot and return it (and save as a resource). |
| browserbase_stagehand_get_urlA | Return the current page URL (full URL with query/fragment). |
| browserbase_stagehand_agentB | Execute a task autonomously using Gemini Computer Use agent. The agent will navigate and interact with web pages to complete the given task. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools have distinct purposes, such as session management (create/close), navigation (navigate/get_url), and interaction (screenshot/act/extract/observe). However, 'browserbase_stagehand_agent' and 'browserbase_stagehand_observe' could cause some confusion as both involve autonomous or guided interaction, though their descriptions help differentiate them.
The naming follows a consistent pattern with 'browserbase_' prefix and snake_case throughout. Most tools use descriptive verb_noun combinations, but there is a minor deviation with 'browserbase_stagehand_agent' which uses 'agent' as a noun instead of a verb, slightly breaking the pattern.
With 9 tools, the count is well-scoped for a browser automation server, covering essential operations like session handling, navigation, interaction, and data extraction. Each tool serves a clear purpose without redundancy, making the set appropriately sized for the domain.
The tool surface provides comprehensive coverage for browser automation, including session lifecycle, navigation, interaction, and data extraction. A minor gap exists in lacking explicit tools for handling browser contexts like tabs or windows, but core workflows are well-supported and agents can work around this.