QA Agent Pro
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
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| navigateC | Navigate to a specific URL in the browser |
| clickB | Click an element on the page identified by a CSS selector |
| typeB | Type text into an input field identified by a CSS selector |
| get_textC | Get the text content of an element |
| screenshotC | Take a screenshot of the current page |
| set_viewportC | Set the browser viewport size (e.g., for mobile simulation) |
| get_console_logsB | Get all console logs captured during the session |
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 7 tools
Each tool has a clearly distinct purpose with no overlap: click, get_console_logs, get_text, navigate, screenshot, set_viewport, and type all target specific, non-overlapping browser automation tasks. An agent can easily tell them apart based on their unique functions.
All tool names follow a consistent verb_noun or verb pattern with snake_case: click, get_console_logs, get_text, navigate, screenshot, set_viewport, and type. This predictable naming scheme makes the set easy to understand and use.
With 7 tools, the count is well-scoped for a QA/browser automation server. Each tool earns its place by covering essential actions like navigation, interaction, and debugging without being overwhelming or too sparse.
The toolset covers core QA workflows: navigation, interaction (click, type), content retrieval (get_text, get_console_logs), and configuration (set_viewport, screenshot). Minor gaps exist, such as missing tools for handling alerts or cookies, but agents can work around these with the provided tools.