General web document search across the Korean-language web index.
AI agents call search_web to retrieve information from Naver Search without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
| Parameter | Type | Required | Description |
|---|---|---|---|
query | string | — | Search query. Must be UTF-8 encoded. |
start | integer | — | Result offset (1-indexed). Default 1, max 1000. |
display | integer | — | Number of results to return per page. Default 10, max 100. |
Parameters from the server's own tool schema.
This tool retrieves and queries data from a search index without modifying, deleting, executing code, or moving money. It is a pure read operation typical of search functionality. The low severity reflects minimal blast radius—an AI agent misusing it would at worst retrieve irrelevant or sensitive public information, not cause destructive or financial harm.
From the tool's definition Tool name is 'search_web' and description states it performs 'General web document search across the Korean-language web index.' The verb 'search' and the action of querying an index for documents are read-only operations with no side effects.
Risk signalsAccepts freeform code/query input (query)
Documented attack patterns abuse exactly the kind of access search_web gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Naver Search, and nothing reaches the server without passing your rules. This is the rule we recommend for search_web:
{
"version": "1",
"default": "deny",
"tools": {
"search_web": {}
}
}search_web is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
General web document search across the Korean-language web index. It is categorised as a Read tool in the Naver Search MCP Server, which means it retrieves data without modifying state.
search_web accepts 3 parameters: query, start, display. The full parameter table on this page comes from the server's own tool schema.
Register the Naver Search MCP server in PolicyLayer and add a rule for search_web: 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. Nothing to install.
search_web is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the search_web 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.
Set action: deny in the PolicyLayer policy for search_web. 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.
search_web is provided by the Naver Search 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.
Start from Naver Search, 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.
12 Naver Search tools catalogued and risk-classified — across an index of 43,000+ MCP servers.