Type text into an input, text area or select an option from a <select> element.
AI agents invoke fill to trigger actions in Chrome Devtools. 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.
Filling in form fields is a browser automation action that produces side effects in a live browser session. It can submit credentials, alter form state, or trigger dynamic page behavior. This falls under Execute as it performs an external browser operation whose effects depend on the arguments provided.
From the tool's definition 'Type text into an input, text area or select an option from a <select> element' — triggers browser interaction/automation actions in a live Chrome browser
Attacks that exploit this kind of access
Type text into an input, text area or select an option from a <select> element. It is categorised as a Execute tool in the Chrome Devtools MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chrome Devtools MCP server in PolicyLayer and add a rule for fill: 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 Chrome Devtools. Nothing to install.
fill 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 fill 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 fill. 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.
fill is provided by the Chrome Devtools MCP server (shivamprasad99/chrome-devtools-mcp). 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 →