search_bunjang
AI agents call search_bunjang to retrieve information from Korean Data without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to search the Bunjang marketplace for data retrieval. Based on the server's purpose ('Real-time Korean web data for AI assistants') and the pattern of sibling tools (all named with 'get_' or 'search_' prefixes), this is a query/read operation with no data modification, deletion, or financial transaction capability.
From the tool's definition Tool name 'search_bunjang' indicates a search operation. Bunjang is a Korean marketplace mentioned in the server description alongside other data retrieval tools (Daangn marketplace, Naver Place reviews, Melon charts, Musinsa rankings).
Attacks that exploit this kind of access
search_bunjang. It is categorised as a Read tool in the Korean Data MCP Server, which means it retrieves data without modifying state.
Register the Korean Data MCP server in PolicyLayer and add a rule for search_bunjang: 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 Data. Nothing to install.
search_bunjang 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_bunjang 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_bunjang. 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_bunjang is provided by the Korean Data MCP server (leadbrain/korean-data-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →