chrome_send_command_to_inject_script · Chrome MCP Server MCP

WHAT IT DOES

What chrome_send_command_to_inject_script does on Chrome MCP Server

AI agents invoke chrome_send_command_to_inject_script 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.

WHY IT NEEDS A POLICY

Why chrome_send_command_to_inject_script needs a policy

Injecting and executing scripts in a browser context is a classic Execute-category action with critical severity. An AI agent could use this to run arbitrary code in any web page, exfiltrate data, manipulate DOM, steal credentials, or perform any browser-level action. The blast radius is extremely high as it bypasses normal browser security boundaries and can affect any open page.

From the tool's definition 'Send commands to injected content scripts' — executes arbitrary JavaScript in the browser context via content script injection

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

chrome_send_command_to_inject_script Rate-limited

chrome_send_command_to_inject_script 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_send_command_to_inject_script": {
      "limits": [
        {
          "counter": "chrome_send_command_to_inject_script_rate",
          "window": "minute",
          "max": 10,
          "scope": "grant"
        }
      ]
    }
  }
}

RATE-LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Chrome MCP Server, so you can run agents against it safely.

FAQ

Questions about chrome_send_command_to_inject_script

What does the chrome_send_command_to_inject_script tool do? +

Send commands to injected content scripts. 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.

How do I enforce a policy on chrome_send_command_to_inject_script? +

Register the Chrome MCP Server MCP server in PolicyLayer and add a rule for chrome_send_command_to_inject_script: 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.

What risk level is chrome_send_command_to_inject_script? +

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

Can I rate-limit chrome_send_command_to_inject_script? +

Yes. Add a rate_limit block to the chrome_send_command_to_inject_script 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_send_command_to_inject_script completely? +

Set action: deny in the PolicyLayer policy for chrome_send_command_to_inject_script. 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_send_command_to_inject_script? +

chrome_send_command_to_inject_script is provided by the Chrome MCP Server MCP server (standbyme626/mcp-chrome). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.