browser_skill

Load agent-browser's own skill/command documentation.

SERVERHercules MCP SOURCE0xmihirk/hercules-mcp

Low RISK CLASS

Category Read

Parameters 00 required

Recommended Allowedsee the rule below

Registry record Grade F, identity unverified Pull the record →

WHAT IT DOES

What browser_skill does on Hercules MCP

AI agents call browser_skill to retrieve information from Hercules MCP without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

RISK

Why browser_skill is rated Low

This tool retrieves documentation/help content about browser skills and commands. It is a read-only operation with no side effects, simply fetching reference material. Despite being on a penetration testing server, this specific tool only loads documentation.

From the tool's definition Load agent-browser's own skill/command documentation

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs browser_skill 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_skill, this is the rule to start with:

browser_skill Allowed

browser_skill is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "browser_skill": {}
  }
}

ALLOW ONLY 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_skill call is checked against it from then on.

FAQ

Questions about browser_skill

What does the browser_skill tool do? +

Load agent-browser's own skill/command documentation. It is categorised as a Read tool in the Hercules MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on browser_skill? +

Register the Hercules MCP server in PolicyLayer and add a rule for browser_skill: 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_skill? +

browser_skill is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit browser_skill? +

Yes. Add a rate_limit block to the browser_skill 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_skill completely? +

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

browser_skill 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 →

Across the catalogue

browser_extract_text on Percepta MCP Server → The MCP Attack Database →

Guides

Roll out MCP under one policy →Data exfiltration →MCP token cost →