Fill form fields with specified data
AI agents use fill_form to create or update resources in Browser MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Browser MCP Server environment.
This tool modifies form data on web pages, fitting the Write category (creates or modifies data reversibly). It is not Destructive because form submissions are typically reversible and can be undone. While it could be part of a larger harmful workflow (especially when combined with 'click_element' or 'execute_javascript'), the tool itself performs reversible data modification.
From the tool's definition The tool 'fill_form' modifies form field data, which creates or updates state on web pages. The description states it 'Fill[s] form fields with specified data', indicating data modification capability.
Attacks that exploit this kind of access
Fill form fields with specified data. It is categorised as a Write tool in the Browser MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Browser MCP Server MCP server in PolicyLayer and add a rule for fill_form: 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 Browser MCP Server. Nothing to install.
fill_form 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_form 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_form. 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_form is provided by the Browser MCP Server MCP server (sac916/claude-browser-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 →