AI agents invoke open_tab to trigger actions in PageMap. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
Given the sibling tools context (browser automation server), 'open_tab' almost certainly opens a new browser tab, which is an external browser operation with side effects. This qualifies as Execute. Severity is medium since opening tabs can trigger navigation to arbitrary URLs, potentially loading malicious content or initiating further actions. Confidence is reduced due to the empty description.
From the tool's definition Tool name 'open_tab' on a server with browser-control sibling tools (close_tab, switch_tab, navigate_back, execute_action, fill_form). Description is empty.
Attacks that exploit this kind of access
open_tab. It is categorised as a Execute tool in the PageMap MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the PageMap MCP server in PolicyLayer and add a rule for open_tab: 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 PageMap. Nothing to install.
open_tab is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the open_tab 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 open_tab. 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.
open_tab is provided by the PageMap MCP server (oci:docker.io/retio1001/pagemap:0.7.3). 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 →