sends keys to an element, aka typing. Clears the field first.
AI agents invoke send_keys to trigger actions in Mcp Selenium. 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.
This tool interacts with a live browser via Selenium WebDriver, performing UI actions (clearing a field and typing into it). This constitutes a browser action with real-world side effects depending on what is typed and into what element — e.g., submitting forms, entering credentials, or triggering search queries. The 'Clears the field first' aspect also modifies existing content.
From the tool's definition sends keys to an element, aka typing. Clears the field first.
Attacks that exploit this kind of access
sends keys to an element, aka typing. Clears the field first. It is categorised as a Execute tool in the Mcp Selenium MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Mcp Selenium MCP server in PolicyLayer and add a rule for send_keys: 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 Mcp Selenium. Nothing to install.
send_keys 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 send_keys 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 send_keys. 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.
send_keys is provided by the Mcp Selenium MCP server (@angiejones/mcp-selenium). 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 →