vibe 코딩 세션의 작업 내용을 마크다운 파일로 기록합니다. 중요한 작업 완료 시 호출하세요.
AI agents use log_session to create or update resources in MCP Token Tracker — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP Token Tracker environment.
The tool writes session activity to a markdown file. This is a reversible write operation (file creation/modification). It does not execute code, delete data, or involve financial transactions. Severity is medium because it writes to the filesystem, which could potentially overwrite existing files or expose session data if misused.
From the tool's definition '마크다운 파일로 기록합니다' (records/writes to a markdown file); '작업 내용을 기록' (records work contents)
Attacks that exploit this kind of access
vibe 코딩 세션의 작업 내용을 마크다운 파일로 기록합니다. 중요한 작업 완료 시 호출하세요. It is categorised as a Write tool in the MCP Token Tracker MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP Token Tracker MCP server in PolicyLayer and add a rule for log_session: 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 MCP Token Tracker. Nothing to install.
log_session 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 log_session 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 log_session. 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.
log_session is provided by the MCP Token Tracker MCP server (kdkim2000/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 →