Refresh the current page.
AI agents invoke refresh to trigger actions in SeleniumMCP. 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.
Refreshing a page is a browser action with potential side effects: it can re-execute JavaScript, resubmit POST requests, trigger network calls, or re-run any page-level automation. It falls under Execute as it triggers an external operation whose effects depend on the current page context. Severity is medium because misuse could cause repeated form submissions or unintended actions on the loaded page.
From the tool's definition 'Refresh the current page' — triggers a browser action that reloads the current page, potentially re-submitting forms, re-triggering scripts, or causing repeated external operations
Attacks that exploit this kind of access
Refresh the current page. It is categorised as a Execute tool in the SeleniumMCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Selenium MCP server in PolicyLayer and add a rule for refresh: 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 SeleniumMCP. Nothing to install.
refresh 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 refresh 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 refresh. 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.
refresh is provided by the Selenium MCP server (lokii0911/seleniummcp). 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 →