Go back
AI agents invoke browser_navigate_back to trigger actions in Browser Pool. 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.
browser_navigate_back performs a navigation action in a Playwright browser session, which executes external operations (loading previous pages, running their JavaScript, fetching resources). While not destructive or financial, it modifies the browser's state and can trigger side effects on the target website.
From the tool's definition Tool navigates browser state by going back in history; this is a browser action that triggers external operations (page loads, script execution on the target site) whose effects depend on which page the user is on.
Attacks that exploit this kind of access
Go back. It is categorised as a Execute tool in the Browser Pool MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Browser Pool MCP server in PolicyLayer and add a rule for browser_navigate_back: 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 Browser Pool. Nothing to install.
browser_navigate_back 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 browser_navigate_back 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 browser_navigate_back. 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.
browser_navigate_back is provided by the Browser Pool MCP server (omgeverdo/browser-pool-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 →