Fill a field selected by CSS selector (no inspect id needed).
AI agents use fill_by_selector to create or update resources in Visual Annotation MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Visual Annotation MCP environment.
This tool creates or modifies data (form inputs) on a web page in a reversible manner. It does not execute arbitrary code, delete data, or move money—it simply enters text into form fields.
From the tool's definition The tool name 'fill_by_selector' and description 'Fill a field selected by CSS selector' indicate it modifies form field values. In the context of a browser automation server, 'fill' means to enter or change data in input fields.
Attacks that exploit this kind of access
Fill a field selected by CSS selector (no inspect id needed). It is categorised as a Write tool in the Visual Annotation MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Visual Annotation MCP server in PolicyLayer and add a rule for fill_by_selector: 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 Visual Annotation MCP. Nothing to install.
fill_by_selector is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the fill_by_selector 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_by_selector. 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_by_selector is provided by the Visual Annotation MCP server (mstocker1/visual_annotation_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 →