browser_cmd

Escape hatch: run any agent-browser subcommand against the stealth session.

SERVERHercules MCP SOURCE0xmihirk/hercules-mcp

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/0xmihirk-hercules-mcp/browser-cmd.md

WHAT IT DOES

What browser_cmd does on Hercules MCP

AI agents invoke browser_cmd to trigger actions in Hercules MCP. 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 browser_cmd is rated High

This tool permits arbitrary execution of browser subcommands with no apparent input validation or sandboxing constraints. In the context of a penetration testing framework, an 'escape hatch' for 'any' subcommand is a direct code/command execution interface.

From the tool's definition Tool description states 'run any agent-browser subcommand' with no restrictions. The 'escape hatch' framing explicitly indicates unrestricted command execution.

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs browser_cmd safely

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

browser_cmd Rate-limited

browser_cmd 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": {
    "browser_cmd": {
      "limits": [
        {
          "counter": "browser_cmd_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 Hercules MCP, apply this rule, and every browser_cmd call is checked against it from then on.

FAQ

Questions about browser_cmd

What does the browser_cmd tool do? +

Escape hatch: run any agent-browser subcommand against the stealth session. It is categorised as a Execute tool in the Hercules MCP 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_cmd? +

Register the Hercules MCP server in PolicyLayer and add a rule for browser_cmd: 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 Hercules MCP. Nothing to install.

What risk level is browser_cmd? +

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

Can I rate-limit browser_cmd? +

Yes. Add a rate_limit block to the browser_cmd 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_cmd completely? +

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

browser_cmd is provided by the Hercules MCP server (0xmihirk/hercules-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Hercules, and thousands of servers like it.

This server

All 45 Hercules tools → High-risk tools on this server →

Across the catalogue

browser_click 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 →