Low Risk

browse_package

Browse classes in a specific Minecraft package. Useful for discovering available classes in a package.

How to control browse_package ↓

AI agents call browse_package to retrieve information from Mcmodding without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

This is a Read operation: it retrieves data about package contents without side effects. Severity is elevated to 'high' (not 'medium') because an AI agent with access to complete package/class discovery could systematically enumerate the entire Minecraft modding surface, map internal APIs, identify security-relevant classes, or discover undocumented capabilities that could support downstream exploitation or…

From the tool's definition Tool 'browse_package' retrieves and queries class information from Minecraft packages ('Browse classes in a specific Minecraft package').

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

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

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "browse_package": {}
  }
}

browse_package is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Mcmodding — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Go deeper

What does the browse_package tool do? +

Browse classes in a specific Minecraft package. Useful for discovering available classes in a package. It is categorised as a Read tool in the Mcmodding MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on browse_package? +

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

What risk level is browse_package? +

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

Can I rate-limit browse_package? +

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

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

browse_package is provided by the Mcmodding MCP server (ogmatrix/mcmodding-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Mcmodding tool call.

Deterministic rules across all 15 Mcmodding tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

Free to start. No card required.

15 Mcmodding tools catalogued and risk-classified — across an index of 42,500+ MCP servers.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.