Click an element using Selenium
AI agents invoke selenium_click to trigger actions in MCP Developer Server. 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.
Selenium click actions execute browser-driven interactions that can trigger arbitrary web operations (form submissions, purchases, deletions, navigation). Running inside a containerized environment reduces but does not eliminate blast radius, as the browser may interact with external services.
From the tool's definition 'Click an element using Selenium' — triggers browser actions via Selenium WebDriver, causing external operations whose effects depend on what element is clicked
Attacks that exploit this kind of access
Click an element using Selenium. It is categorised as a Execute tool in the MCP Developer Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the MCP Developer Server MCP server in PolicyLayer and add a rule for selenium_click: 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 Developer Server. Nothing to install.
selenium_click 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 selenium_click 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 selenium_click. 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.
selenium_click is provided by the MCP Developer Server MCP server (ra86-dev/mcpdev-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 →