모든 습관과 최근 7일 기록을 보여줍니다.
AI agents call db_habit_list to retrieve information from K-Personal MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries a personal SQLite database to retrieve habit data and historical logs. It performs no side effects, creates no data, executes no code, and deletes nothing. The operation is read-only and informational in nature, making it a Read category tool with low severity since misuse would only expose existing personal habit data rather than cause irreversible damage or execute arbitrary operations.
From the tool's definition Tool name 'db_habit_list' and description indicating it 'shows all habits and recent 7-day records' — purely a data retrieval operation with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
모든 습관과 최근 7일 기록을 보여줍니다. It is categorised as a Read tool in the K-Personal MCP MCP Server, which means it retrieves data without modifying state.
Register the K-Personal MCP server in PolicyLayer and add a rule for db_habit_list: 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 K-Personal MCP. Nothing to install.
db_habit_list 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 db_habit_list 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 db_habit_list. 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.
db_habit_list is provided by the K-Personal MCP server (lee30934-byte/k-personal-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 →