Low Risk

search_local

πŸ“ Search for local businesses, restaurants, and places in Korea. Find location information, reviews, contact details, and business hours for Korean establishments. For current business hours or today

How to control search_local ↓

What search_local does on Naver Search MCP Server

AI agents call search_local to retrieve information from Naver Search MCP Server without modifying anything β€” typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Low Risk

Why search_local needs a policy

This tool retrieves public business information (locations, reviews, hours, contact details) from Naver's local search database without creating, modifying, deleting, or executing operations. It is a read-only query operation with minimal security riskβ€”the worst-case scenario is exposure of already-public business directory data.

From the tool's definition Tool description states 'Search for local businesses, restaurants, and places' and 'Find location information, reviews, contact details, and business hours'. The verb 'search' and 'find' indicate data retrieval with no modification or side effects.

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

How to control search_local

PolicyLayer is an MCP gateway β€” it sits between your AI agents and Naver Search MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for search_local:

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

search_local is read-only, so it stays allowed β€” but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Naver Search MCP Server β€” nothing to install.
  2. Add this policy β€” 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 search_local

What does the search_local tool do? +

πŸ“ Search for local businesses, restaurants, and places in Korea. Find location information, reviews, contact details, and business hours for Korean establishments. For current business hours or today. It is categorised as a Read tool in the Naver Search MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on search_local? +

Register the Naver Search MCP Server MCP server in PolicyLayer and add a rule for search_local: 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 Naver Search MCP Server. Nothing to install.

What risk level is search_local? +

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

Can I rate-limit search_local? +

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

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

search_local is provided by the Naver Search MCP Server MCP server (isnow890/naver-search-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

Enforce policy on every Naver Search MCP Server tool call.

Start from Naver Search MCP Server, 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.

21 Naver Search MCP Server tools catalogued and risk-classified β€” 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.