@pokutuna/mcp-chrome-tabs
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EXCLUDE_HOSTS | No | Comma-separated list of domains to exclude from tab listing and content access | |
| CHECK_INTERVAL | No | Interval in milliseconds to check for tab changes and notify clients (set to 0 to disable) | 3000 |
| APPLICATION_NAME | No | Application name to control | Google Chrome |
| EXPERIMENTAL_BROWSER | No | Experimental browser support (e.g., 'safari') |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Use this server to access the user's open browser tabs.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_tabsA | List all open tabs in the user's browser with their titles and tab references. |
| read_tab_contentA | Get readable content from a tab in the user's browser. Provide ID (from list_tabs output) to read a specific tab, or omit for the active tab. |
| open_in_new_tabB | Open a URL in a new tab to present content or enable user interaction with webpages |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| current_tab | Content of the currently active tab in the user's browser |
TDQS
Scored across 3 tools
Each tool has a clearly distinct purpose: listing tabs, reading tab content, and opening a new tab. There is no meaningful overlap or ambiguity between them.
All tool names follow a consistent snake_case verb_noun pattern: list_tabs, read_tab_content, open_in_new_tab. The convention is predictable and readable.
Three tools is well-scoped for a browser-tab MCP server focused on listing, reading, and opening tabs. Each tool earns its place without feeling thin or bloated.
The surface covers the core read/open workflows, but missing operations like closing tabs or focusing an existing tab could limit some agent workflows. These are minor gaps that agents can mostly work around.