list_tabs
Read open Chrome tabs. Returns a domain histogram (the fastest way to understand a large tab set) plus a detailed view. When summarizing the results for the user, you should include the histogram bar graph in your response. Filter with query, reshape with group_by, or isolate redundant tabs with ...
This record as markdown: /tools/2manytabs-mcp-host/list-tabs.md
What list_tabs does on 2manytabs Mcp Host
AI agents call list_tabs to retrieve information from 2manytabs Mcp Host without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | — | Case-insensitive substring; keep only tabs whose title or URL contains it. |
group_by | string | — | Shape of the detailed view. 'domain' (default) is best for triaging many tabs; 'window' groups by browser window; 'none' returns a flat list. |
duplicates_only | boolean | — | Only include tabs that are duplicates (share a URL with an earlier tab). |
Parameters from the server's own tool schema.
Why list_tabs is rated Low
Even though list_tabs only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs list_tabs safely
PolicyLayer is an MCP gateway: it sits between your AI agents and 2manytabs Mcp Host, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For list_tabs, this is the rule to start with:
list_tabs is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect 2manytabs Mcp Host, apply this rule, and every list_tabs call is checked against it from then on.
Questions about list_tabs
Read open Chrome tabs. Returns a domain histogram (the fastest way to understand a large tab set) plus a detailed view. When summarizing the results for the user, you should include the histogram bar graph in your response. Filter with query, reshape with group_by, or isolate redundant tabs with duplicates_only. Read-only — never closes anything. It is categorised as a Read tool in the 2manytabs Mcp Host MCP Server, which means it retrieves data without modifying state.
list_tabs accepts 3 parameters: query, group_by, duplicates_only. The full parameter table on this page comes from the server's own tool schema.
Register the 2manytabs Mcp Host MCP server in PolicyLayer and add a rule for list_tabs: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches 2manytabs Mcp Host. Nothing to install.
list_tabs is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the list_tabs rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for list_tabs. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
list_tabs is provided by the 2manytabs Mcp Host MCP server (2manytabs-mcp-host). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on 2manytabs Mcp Host, and thousands of servers like it.
This server
Across the catalogue