mcp-browser-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HEADLESS | No | Run browser in headless mode (local only) | true |
| ANCHOR_API_KEY | No | AnchorBrowser API key | |
| BROWSER_PROVIDER | No | Browser provider: local, anchorbrowser, browserbase | local |
| SCREENSHOT_FORMAT | No | Screenshot format: png or jpeg | png |
| SESSION_TIMEOUT_MS | No | Browser session timeout (5 min) | 300000 |
| BROWSERBASE_API_KEY | No | Browserbase API key |
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_navigateA | Navigate the browser to a URL. Returns the page title and current URL after navigation. |
| browser_screenshotA | Take a screenshot of the current browser page. Returns a base64-encoded PNG image. |
| browser_clickB | Click on an element in the browser. Can target by CSS selector, text content, or ARIA label. |
| browser_typeB | Type text into an input field or textarea. |
| browser_get_contentA | Get the text content or HTML of the current page or a specific element. |
| browser_evaluateA | Execute JavaScript in the browser and return the result. Useful for complex extractions. |
| browser_waitC | Wait for an element to appear on the page. |
| browser_scrollC | Scroll the page or an element. |
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 8 tools
Each tool has a distinct action (click, type, navigate, etc.) with clear descriptions, making them easily distinguishable for an agent.
All tools follow a consistent `browser_verb` snake_case pattern, making naming predictable and easy to remember.
8 tools cover core browser interactions without being excessive, well-scoped for the purpose of browser automation.
Covers essential operations like navigation, clicking, typing, scrolling, and content extraction. Missing features like browser back/forward or dialog handling, but covers the main workflows.