Track an activity for a specific habit on a given date
AI agents use track_habit to create or update resources in LunaTask MCP Server — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your LunaTask MCP Server environment.
track_habit creates or records a new activity entry in the habit-tracking system. This is a data modification that is reversible (the tracked activity could be untracked or edited later), making it a Write-class operation.
From the tool's definition The tool description states it 'Track[s] an activity for a specific habit on a given date', which modifies habit tracking data by recording a new activity entry. This is a reversible create/update operation, consistent with the Write category.
Documented attack patterns abuse exactly the kind of access track_habit gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and LunaTask MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for track_habit:
{
"version": "1",
"default": "deny",
"tools": {
"track_habit": {
"limits": [
{
"counter": "track_habit_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}track_habit stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Track an activity for a specific habit on a given date. It is categorised as a Write tool in the LunaTask MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the LunaTask MCP Server MCP server in PolicyLayer and add a rule for track_habit: 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 LunaTask MCP Server. Nothing to install.
track_habit 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 track_habit 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 track_habit. 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.
track_habit is provided by the LunaTask MCP Server MCP server (tensorfreitas/lunatask-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from LunaTask MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
12 LunaTask MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.