과거 KDA 대화 이력(conversations.db)에서 메시지를 검색합니다.
AI agents call db_convo_search 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 retrieves/queries historical conversation data from a local SQLite database without modifying, deleting, or executing arbitrary operations. It is a read-only search function with minimal blast radius if misused—an agent could retrieve personal conversation history but cannot alter, delete, or execute commands. Classified as Read with low severity.
From the tool's definition Tool name 'db_convo_search' and description indicate a search operation ('검색합니다' = 'search') on a database of past conversations. No modification, deletion, or execution of code is described.
Attacks that exploit this kind of access
과거 KDA 대화 이력(conversations.db)에서 메시지를 검색합니다. 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_convo_search: 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_convo_search 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_convo_search 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_convo_search. 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_convo_search 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 →