~/.kda/memory/<name>.md 에 내용을 기록합니다. 재사용 패턴은 skill_<이름>,
AI agents use db_memory_write to create or update resources in K-Personal MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your K-Personal MCP environment.
This tool creates or modifies markdown files in a personal database directory. It is a Write operation as it stores data reversibly in markdown format. Severity is medium because it affects personal data storage on the local system, and misuse could overwrite important notes or memory entries.
From the tool's definition Tool writes content to ~/.kda/memory/<name>.md file with reuse pattern skill_<name>. The description states '기록합니다' (writes/records) indicating data creation/modification.
Attacks that exploit this kind of access
~/.kda/memory/<name>.md 에 내용을 기록합니다. 재사용 패턴은 skill_<이름>,. It is categorised as a Write tool in the K-Personal MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the K-Personal MCP server in PolicyLayer and add a rule for db_memory_write: 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_memory_write is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the db_memory_write 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_memory_write. 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_memory_write 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 →