browser_curl

THE RISK

High Risk

Why browser_curl needs a policy

This tool executes HTTP requests via a browser session, which constitutes an external operation with effects that depend on the arguments (method, URL, headers, body). It could be used to trigger arbitrary web actions, interact with authenticated sessions, exfiltrate data, or perform state-changing requests on external services.

From the tool's definition 'Send an HTTP request through an existing Kernel browser session' — triggers external HTTP operations through a live browser session

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

POLICY

How to control browser_curl

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

policy.json

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

browser_curl 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 Kernel MCP Server — 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

Related tools and policies

More Kernel MCP Server tools

Execute computer_action Execute computer actions on a browser session. Pass a single action for simple operations Execute exec_command Execute a command synchronously inside a browser VM. Returns stdout, stderr, and exit code Execute execute_playwright_code Execute Playwright/TypeScript automation code against a Kernel browser session. If session Execute manage_apps Manage Kernel apps, deployments, and invocations. Use Execute manage_browser_pools Manage pools of pre-warmed browser instances for fast acquisition. Use Execute manage_browsers Manage browser sessions in the Kernel platform. Use action Write manage_api_keys Manage Kernel API keys. Use Write manage_auth_connections Manage Kernel managed auth connections for keeping a profile logged into a third-party sit

All 16 Kernel MCP Server tools →

Execute tools on other servers

Android Forensics ADB MCP Server adb_shell_command EMBA-MCP run_emba_scan Frida Game Hacking MCP remove_breakpoint Procmon request_elevation

Go deeper

High-risk tools in Kernel MCP Server → 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.
Agent sandbox → Bounding what an agent can execute and where the boundary should sit.
Least privilege for MCP → Granting agents the minimum tool surface the task needs.
Rate Limiting MCP Tool Calls: A Practical Guide →
MCP Security: Why Prompt Guardrails Aren't Enough →

FAQ

Questions about browser_curl

What does the browser_curl tool do? +

Send an HTTP request through an existing Kernel browser session. It is categorised as a Execute tool in the Kernel 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 browser_curl? +

Register the Kernel MCP Server MCP server in PolicyLayer and add a rule for browser_curl: 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 Kernel MCP Server. Nothing to install.

What risk level is browser_curl? +

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

Can I rate-limit browser_curl? +

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

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

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

Enforce policy on every Kernel MCP Server tool call.

Start from Kernel MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.

CHECK YOUR STACK →