filter_statistics
AI agents call filter_statistics to retrieve information from Korean Stat without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool appears to filter statistical data from the KOSIS OpenAPI. Filtering is a read operation that queries or narrows existing data without modification, creation, or deletion. The absence of a description is mitigated by the consistent pattern of read-only operations across all sibling tools on this statistical data server. No evidence of side effects, code execution, or data modification.
From the tool's definition Tool name 'filter_statistics' combined with server purpose of enabling clients to 'search, retrieve, and analyze Korean statistical data.' Sibling tools all perform read operations (aggregate_statistics, browse_categories, get_statistics_data,…
Attacks that exploit this kind of access
filter_statistics. It is categorised as a Read tool in the Korean Stat MCP Server, which means it retrieves data without modifying state.
Register the Korean Stat MCP server in PolicyLayer and add a rule for filter_statistics: 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 Stat. Nothing to install.
filter_statistics 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 filter_statistics 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 filter_statistics. 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.
filter_statistics is provided by the Korean Stat MCP server (seolcoding/korean-stat-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 →