Run a pruning prescription on the current session. Args: prescription: Prescription tier — 'gentle', 'standard', or 'aggressive'. execute: If False (default), dry-run only. If True, apply changes with backup.
AI agents use treat_session to create or update resources in Cozempic — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cozempic environment.
This tool modifies the current session by pruning its contents. When execute=True, it applies changes (though a backup is made, suggesting some reversibility). The backup mitigates destructive risk, placing this in Write rather than Destructive. Misuse could corrupt or truncate an active session, hence medium severity.
From the tool's definition 'Run a pruning prescription on the current session' and 'If True, apply changes with backup'
Documented attack patterns abuse exactly the kind of access treat_session gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Cozempic, and nothing reaches the server without passing your rules. This is the rule we recommend for treat_session:
{
"version": "1",
"default": "deny",
"tools": {
"treat_session": {
"limits": [
{
"counter": "treat_session_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}treat_session 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.
Run a pruning prescription on the current session. Args: prescription: Prescription tier — 'gentle', 'standard', or 'aggressive'. execute: If False (default), dry-run only. If True, apply changes with backup. It is categorised as a Write tool in the Cozempic MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cozempic MCP server in PolicyLayer and add a rule for treat_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 Cozempic. Nothing to install.
treat_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 treat_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 treat_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.
treat_session is provided by the Cozempic MCP server (ruya-ai/cozempic). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 5 Cozempic tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
5 Cozempic tools catalogued and risk-classified — across an index of 42,500+ MCP servers.