Enhanced Browser MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| BROWSER_WS_ENDPOINT | No | WebSocket endpoint for the browser to connect to. | ws://localhost:8080/ws |
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 | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_navigateB | Navigate to a URL |
| browser_go_backA | Go back to the previous page |
| browser_go_forwardA | Go forward to the next page |
| browser_snapshotA | Capture accessibility snapshot of the current page. Use this for getting references to elements to interact with. |
| browser_clickB | Perform click on a web page |
| browser_hoverC | Hover over element on page |
| browser_typeC | Type text into editable element |
| browser_select_optionB | Select an option in a dropdown |
| browser_press_keyB | Press a key on the keyboard |
| browser_waitB | Wait for a specified time in seconds |
| browser_get_console_logsA | Get the console logs from the browser |
| browser_screenshotC | Take a screenshot of the current page |
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 12 tools
Each tool targets a distinct browser action: navigation, history, interaction, state inspection, and waiting. Snapshot and screenshot are clearly separated (accessibility tree vs visual capture), and no two tools overlap in purpose.
All tools follow the browser_verb_noun pattern consistently, using lowercase and underscores. The verb clearly indicates the action (navigate, click, type, wait), making the set predictable and easy to navigate.
With 12 tools, the server is well-scoped for browser automation, covering essential actions without unnecessary bloat. This fits comfortably within the ideal range, and each tool earns its place.
The set covers core browser workflows: navigation, history, interaction, state reading, and waiting. Minor gaps exist (e.g., explicit scroll or page reload), but agents can work around them, making the surface reasonably complete for basic automation.