BrowserTools MCP
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 |
|---|---|
| getConsoleLogsC | Check our browser logs |
| getConsoleErrorsC | Check our browsers console errors |
| getNetworkErrorsC | Check our network ERROR logs |
| getNetworkLogsC | Check ALL our network logs |
| takeScreenshotB | Take a screenshot of the current browser tab |
| getSelectedElementB | Get the selected element from the browser |
| wipeLogsB | Wipe all browser logs from memory |
| runAccessibilityAuditB | Run an accessibility audit on the current page |
| runPerformanceAuditB | Run a performance audit on the current page |
| runSEOAuditB | Run an SEO audit on the current page |
| runNextJSAuditD | – |
| runDebuggerModeC | Run debugger mode to debug an issue in our application |
| runAuditModeB | Run audit mode to optimize our application for SEO, accessibility and performance |
| runBestPracticesAuditB | Run a best practices audit on 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 14 tools
There is significant overlap between tools, particularly in the audit category where runAuditMode appears to encompass SEO, accessibility, and performance audits that have separate dedicated tools, creating confusion. However, the console and network tools are more distinct in their focus areas, and descriptions help clarify some boundaries.
Most tools follow a consistent verb_noun pattern (e.g., getConsoleErrors, runAccessibilityAudit, takeScreenshot), with clear action-oriented names. The main deviation is runAuditMode, which uses a more generic 'Mode' suffix, but overall the naming is predictable and readable.
With 14 tools, the count is reasonable for a browser testing and debugging domain, covering areas like logs, audits, debugging, and screenshots. It's slightly on the higher side but well-scoped for the purpose, with each tool having a defined role in browser interaction.
The toolset covers key browser operations like logging, auditing, and screenshots, but has notable gaps. For example, there are no tools for navigation (e.g., navigate_to_url, refresh_page) or element interaction (e.g., click_element, input_text), which are essential for comprehensive browser automation, limiting agent workflows.