Low Risk

discover_tools

List all currently wired tools in this MCP build.

How to control discover_tools ↓

What discover_tools does on Korean Land MCP

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

Low Risk

Why discover_tools needs a policy

This tool only reads and returns a list of available tools in the MCP build. It performs no data modification, execution, or deletion. The blast radius of misuse is negligible — it only exposes tool names/metadata.

From the tool's definition 'List all currently wired tools' — purely retrieves metadata about available tools with no side effects

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

How to control discover_tools

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

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

discover_tools 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 Korean Land MCP — 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.

Related tools and policies

Go deeper

Questions about discover_tools

What does the discover_tools tool do? +

List all currently wired tools in this MCP build. It is categorised as a Read tool in the Korean Land MCP MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on discover_tools? +

Register the Korean Land MCP server in PolicyLayer and add a rule for discover_tools: 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 Korean Land MCP. Nothing to install.

What risk level is discover_tools? +

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

Can I rate-limit discover_tools? +

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

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

discover_tools is provided by the Korean Land MCP server (urbanwatcherkr/korean-land-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Korean Land MCP tool call.

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

Free to start. No card required.

8 Korean Land MCP tools catalogued and risk-classified — across an index of 43,000+ 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.