AI agents invoke browser_go_back to trigger actions in Browser. 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.
Navigating back in browser history triggers a page load and changes browser state, which is an external browser operation with potential side effects (e.g., re-submitting forms, triggering navigation events). It goes beyond a simple read operation as it actively controls the browser's state and could cause unintended page transitions or data submissions.
From the tool's definition Navigate back in history
Attacks that exploit this kind of access
Navigate back in history (see browser_docs). It is categorised as a Execute tool in the Browser MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Browser MCP server in PolicyLayer and add a rule for browser_go_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. Nothing to install.
browser_go_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_go_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_go_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_go_back is provided by the Browser MCP server (ricardodeazambuja/browser-mcp-server). 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 →