send_keys

THE RISK

High Risk

On a browser automation MCP server, 'send_keys' almost certainly sends keyboard input to the browser (e.g., key presses, shortcuts, text entry). This constitutes executing browser actions with effects that depend on arguments — for example, sending keyboard shortcuts could trigger arbitrary browser or OS-level actions.

From the tool's definition Tool name 'send_keys' on a browser automation server; sibling tools include click_element, input_text, go_to_url — all browser interaction tools

Documented attack patterns abuse exactly the kind of access send_keys gives an agent:

HOW TO CONTROL SEND_KEYS

PolicyLayer is an MCP gateway — it sits between your AI agents and Mcp Browser Use, and nothing reaches the server without passing your rules. This is the rule we recommend for send_keys:

policy.json

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

send_keys 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.

Create a free account and register Mcp Browser Use — nothing to install.
Add this policy — paste it, or build it visually.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

RATE-LIMIT THIS TOOL →

Free to start. No card required.

EXPLORE

More Mcp Browser Use tools

Execute initialize_browser Initialize a new browser instance. Args: headless: Whether to run browser in h Execute wait Wait for the specified number of seconds. Args: seconds (int, optional): Numbe Execute search_google Search the query in Google in the current tab. Args: query (str): The search q Execute click_element Click the element with the specified index. Args: index (int): The index of th Execute go_back Go back to the previous page. Returns: str: A message confirming navigation ba Execute go_to_url Navigate to URL in the current tab. Args: url (str): The URL to navigate to Execute input_text Input text into an interactive element at the specified index. Args: index (in Execute open_tab Open a URL in a new tab. Args: url (str): The URL to open in the new tab R

All 19 Mcp Browser Use tools →

Execute tools on other servers

Frida Game Hacking MCP remove_breakpoint Procmon request_elevation WireMCP capture_packets Pentest Ai run_probe

Go deeper

High-risk tools in Mcp Browser Use → Every high-risk tool this server exposes, in one view.
All high-risk MCP tools → Every high-risk tool across the catalogue, and the policy pattern that contains them.
The MCP Attack Database → Documented attack patterns against MCP deployments — and the policies that stop them.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

What does the send_keys tool do? +

send_keys. It is categorised as a Execute tool in the Mcp Browser Use MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.

How do I enforce a policy on send_keys? +

Register the Mcp Browser Use MCP server in PolicyLayer and add a rule for send_keys: 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 Mcp Browser Use. Nothing to install.

What risk level is send_keys? +

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

Can I rate-limit send_keys? +

Yes. Add a rate_limit block to the send_keys 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 send_keys completely? +

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

send_keys is provided by the Mcp Browser Use MCP server (vinayak-mehta/mcp-browser-use). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcp Browser Use tool call.

Deterministic rules across all 19 Mcp Browser Use tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

GOVERN MCP BROWSER USE →

Free to start. No card required.

19 Mcp Browser Use tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// WHAT SEND_KEYS ON MCP BROWSER USE DOES

// THE RISK

// HOW TO CONTROL SEND_KEYS

// EXPLORE