Get the tab ID of the page
AI agents call get_tab_id to retrieve information from Chrome Devtools without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves information (a tab identifier) with no side effects. It does not create, modify, delete, execute code, or move resources. It is a straightforward read operation analogous to 'get' or 'fetch' patterns. Even in the context of browser automation, retrieving a tab ID is informational only; the actual control actions (click, fill, evaluate_script) are separate tools.
From the tool's definition Tool name is 'get_tab_id' and description states 'Get the tab ID of the page' — a pure query operation that retrieves metadata about an open tab without modifying state or triggering external operations.
Attacks that exploit this kind of access
Get the tab ID of the page. It is categorised as a Read tool in the Chrome Devtools MCP Server, which means it retrieves data without modifying state.
Register the Chrome Devtools MCP server in PolicyLayer and add a rule for get_tab_id: 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 Chrome Devtools. Nothing to install.
get_tab_id 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_tab_id 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_tab_id. 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_tab_id is provided by the Chrome Devtools MCP server (nimbus21/chrome-devtools-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →