chrome_fill_input

Fill text into an input field

SERVERChrome Feedback SOURCE2019-02-18/mcx

High RISK CLASS

Category Execute

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/2019-02-18-mcx/chrome-fill-input.md

WHAT IT DOES

What chrome_fill_input does on Chrome Feedback

AI agents invoke chrome_fill_input to trigger actions in Chrome Feedback. 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.

RISK

Why chrome_fill_input is rated High

Filling an input field is a browser action that modifies the state of a web page element and can trigger form validation, event listeners, or autofill behaviors. It falls under Execute as it interacts with external browser operations whose effects depend on what field is targeted and what content is entered. It spans Write but Execute is more appropriate given it's a browser automation action.

From the tool's definition Fill text into an input field

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs chrome_fill_input safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Chrome Feedback, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For chrome_fill_input, this is the rule to start with:

chrome_fill_input Rate-limited

chrome_fill_input stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "chrome_fill_input": {
      "limits": [
        {
          "counter": "chrome_fill_input_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Chrome Feedback, apply this rule, and every chrome_fill_input call is checked against it from then on.

FAQ

Questions about chrome_fill_input

What does the chrome_fill_input tool do? +

Fill text into an input field. It is categorised as a Execute tool in the Chrome Feedback MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on chrome_fill_input? +

Register the Chrome Feedback MCP server in PolicyLayer and add a rule for chrome_fill_input: 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 Feedback. Nothing to install.

What risk level is chrome_fill_input? +

chrome_fill_input is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.

Can I rate-limit chrome_fill_input? +

Yes. Add a rate_limit block to the chrome_fill_input 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.

How do I block chrome_fill_input completely? +

Set action: deny in the PolicyLayer policy for chrome_fill_input. 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.

What MCP server provides chrome_fill_input? +

chrome_fill_input is provided by the Chrome Feedback MCP server (2019-02-18/mcx). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Chrome Feedback, and thousands of servers like it.

This server

All 16 Chrome Feedback tools → High-risk tools on this server →

Across the catalogue

browser_fill on Percepta MCP Server → All high-risk MCP tools → The MCP Attack Database →

Guides

Govern code and CI agents →Agent sandbox →Least privilege for MCP →