AI agents invoke browser_reload 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.
Reloading a page is an external browser operation that can re-execute JavaScript, re-submit POST forms, and trigger server-side side effects. It goes beyond passive reading and qualifies as Execute. Severity is medium because misuse could inadvertently resubmit transactions or disrupt user sessions, but the blast radius is generally bounded to the current page context.
From the tool's definition Reload the current page — triggers a browser navigation/network action that re-executes page load, scripts, and may re-submit forms or re-trigger side effects depending on page state.
Attacks that exploit this kind of access
Reload the current page (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_reload: 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_reload 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_reload 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_reload. 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_reload 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 →