mcp-browser-testing-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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 | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| browser_navigateB | Navigate the headless browser to an HTTP or HTTPS URL. |
| browser_inspectA | Automatically identify visible input areas, buttons, and links on the current page, including human-readable labels and stable selectors. |
| browser_interactC | Click, type into, or scroll an element into view using a CSS or XPath selector. |
| browser_screenshotB | Capture a PNG screenshot of the whole page, viewport, or a selected 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 4 tools
Each tool maps to a distinct browser action: navigation, inspection, interaction, and screenshot capture. There is no meaningful overlap between inspecting elements and interacting with them, since one discovers selectors and the other acts on them.
All tools use the same browser_ prefix followed by a concise action-oriented name. browser_screenshot uses a noun form, but it is conventionally understood as an action and does not break the overall pattern.
Four tools is well within the ideal range and each tool has a clear role in the core browser testing loop. The surface is compact without feeling arbitrarily truncated.
The core workflow of navigate, inspect, interact, and screenshot is covered, but important browser-testing operations are missing, such as waiting for elements or page load, extracting text, capturing console/network errors, and closing the browser session. These gaps could cause flaky automation or dead ends.