Concurrent Browser 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 |
|---|---|
| browser_create_instanceC | Create a new browser instance |
| browser_list_instancesB | List all browser instances |
| browser_close_instanceC | Close the specified browser instance |
| browser_close_all_instancesB | Close all browser instances |
| browser_navigateC | Navigate to a specified URL |
| browser_go_backC | Go back to the previous page |
| browser_go_forwardC | Go forward to the next page |
| browser_refreshC | Refresh the current page |
| browser_clickC | Click on a page element |
| browser_typeC | Type text into an element |
| browser_fillC | Fill a form field |
| browser_select_optionC | Select an option from a dropdown |
| browser_get_page_infoC | Get detailed page information including full HTML content, page statistics, and metadata |
| browser_get_element_textC | Get element text content |
| browser_get_element_attributeC | Get element attribute value |
| browser_screenshotC | Take a screenshot of the page or element |
| browser_wait_for_elementC | Wait for an element to appear |
| browser_wait_for_navigationB | Wait for page navigation to complete |
| browser_evaluateC | Execute JavaScript code in the page context |
| browser_get_markdownC | Get page content in Markdown format, optimized for large language models |
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 20 tools
Every tool has a clearly distinct purpose with no ambiguity. Each tool targets a specific browser interaction (e.g., navigation, element interaction, instance management, content retrieval), and the descriptions clearly differentiate their functions. There is no overlap that would cause misselection.
All tool names follow a consistent 'browser_' prefix with snake_case and descriptive verb_noun patterns (e.g., browser_click, browser_navigate, browser_get_markdown). This predictability makes it easy for agents to understand and use the tools without confusion.
With 20 tools, the count is slightly high but reasonable for a comprehensive browser automation server. It covers a wide range of operations from basic navigation to advanced interactions, though it might feel heavy compared to simpler servers. Each tool appears to earn its place in the domain.
The tool set provides complete coverage for browser automation, including instance management, navigation, element interaction, content retrieval, and waiting mechanisms. There are no obvious gaps; agents can perform full workflows from setup to teardown without dead ends.