AI agents call search_accredited_labs to retrieve information from Kolas without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and retrieves information about accredited laboratories from public Korean government databases (knab.go.kr + data.go.kr). It performs a search operation that returns data without side effects, modification, or execution of external operations. The search is over static accreditation records, making it a Read category tool with low severity risk.
From the tool's definition Tool name 'search_accredited_labs' and description 'Search KOLAS-accredited laboratories by free-text query' indicate retrieval/query of publicly available laboratory accreditation data with no modification or execution capabilities.
Attacks that exploit this kind of access
Search KOLAS-accredited laboratories by free-text query and. It is categorised as a Read tool in the Kolas MCP Server, which means it retrieves data without modifying state.
Register the Kolas MCP server in PolicyLayer and add a rule for search_accredited_labs: 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 Kolas. Nothing to install.
search_accredited_labs 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_accredited_labs 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_accredited_labs. 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_accredited_labs is provided by the Kolas MCP server (vertical-mcp/kolas-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 →