Fill forms and select options
AI agents invoke chrome_fill_or_select to trigger actions in Chrome MCP 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.
Form filling is an active browser manipulation action that can trigger side effects such as submitting credentials, personal data, or initiating workflows on external sites. It goes beyond reading or simple writing since it interacts with live browser sessions and can cause cascading actions depending on form content.
From the tool's definition Fill forms and select options — directly manipulates browser form elements, triggering input events and potentially submitting data to external services
Attacks that exploit this kind of access
Fill forms and select options. It is categorised as a Execute tool in the Chrome MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Chrome MCP Server MCP server in PolicyLayer and add a rule for chrome_fill_or_select: 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 MCP Server. Nothing to install.
chrome_fill_or_select 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 chrome_fill_or_select 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 chrome_fill_or_select. 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.
chrome_fill_or_select is provided by the Chrome MCP Server MCP server (mnisred/mcp-chrome). 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 →