AI agents use daily_check_in to create or update resources in Pelaris — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Pelaris environment.
The tool name 'daily_check_in' and the partial description 'Log how you' strongly suggest this tool records a daily wellness or readiness check-in (e.g., mood, sleep, fatigue). This is a Write operation — creating a new log entry — with low severity since it only records personal fitness/wellness data and has no destructive or financial implications. Confidence is slightly reduced due to the truncated description.
From the tool's definition 'Log how you' — the description is truncated but begins with 'Log', indicating it writes/records data (a daily check-in entry).
Attacks that exploit this kind of access
Log how you. It is categorised as a Write tool in the Pelaris MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Pelaris MCP server in PolicyLayer and add a rule for daily_check_in: 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 Pelaris. Nothing to install.
daily_check_in 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 daily_check_in 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 daily_check_in. 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.
daily_check_in is provided by the Pelaris MCP server (thedonk/pelaris-mcp-server). 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 →