Get all open tabs from Google Chrome browser with unique tab IDs. Each tab has a stable, unique ID that persists across browser operations. Output shows both display format (1-1, 1-2) and Tab ID [Tab ID: 1234567890] for each tab. ALWAYS use the Tab ID number for reliable operations.
AI agents call get_tabs to retrieve information from MCP Browser Tabs Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool purely retrieves data about open Chrome tabs without causing any side effects, modifications, or control actions. While it could reveal sensitive information that users have open (user privacy concern), the technical risk category is Read. The low severity reflects that reading tab metadata has limited direct harm compared to actually controlling or modifying tabs.
From the tool's definition Tool description states it 'Get all open tabs from Google Chrome browser' and 'retrieve information'. No modification, deletion, execution, or financial operations are described. The tool only queries and returns information about existing tabs.
Documented attack patterns abuse exactly the kind of access get_tabs gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP Browser Tabs Server, and nothing reaches the server without passing your rules. This is the rule we recommend for get_tabs:
{
"version": "1",
"default": "deny",
"tools": {
"get_tabs": {}
}
}get_tabs is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Get all open tabs from Google Chrome browser with unique tab IDs. Each tab has a stable, unique ID that persists across browser operations. Output shows both display format (1-1, 1-2) and Tab ID [Tab ID: 1234567890] for each tab. ALWAYS use the Tab ID number for reliable operations. It is categorised as a Read tool in the MCP Browser Tabs Server MCP Server, which means it retrieves data without modifying state.
Register the MCP Browser Tabs Server MCP server in PolicyLayer and add a rule for get_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 MCP Browser Tabs Server. Nothing to install.
get_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 get_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 get_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.
get_tabs is provided by the MCP Browser Tabs Server MCP server (kazuph/mcp-browser-tabs). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from MCP Browser Tabs Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
4 MCP Browser Tabs Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.