Diagnose the current Claude Code session for context bloat. Returns token count, context window usage %, bloat breakdown by message type, and estimated savings for each prescription tier (gentle/standard/aggressive). Use this when context is getting heavy or the user asks about session health.
AI agents call diagnose_current to retrieve information from Cozempic without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes diagnostic metrics about the current session state without altering any data or triggering external operations. It is purely informational, supporting introspection into session health. The low severity reflects minimal blast radius—misuse cannot corrupt data, execute code, or cause harm beyond wasting a query.
From the tool's definition Tool 'diagnose_current' returns diagnostic information: 'token count, context window usage %, bloat breakdown by message type, and estimated savings'. All verbs are read-only (Returns, Use this when...).
Documented attack patterns abuse exactly the kind of access diagnose_current 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 diagnose_current:
{
"version": "1",
"default": "deny",
"tools": {
"diagnose_current": {}
}
}diagnose_current is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Diagnose the current Claude Code session for context bloat. Returns token count, context window usage %, bloat breakdown by message type, and estimated savings for each prescription tier (gentle/standard/aggressive). Use this when context is getting heavy or the user asks about session health. It is categorised as a Read tool in the Cozempic MCP Server, which means it retrieves data without modifying state.
Register the Cozempic MCP server in PolicyLayer and add a rule for diagnose_current: 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.
diagnose_current is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the diagnose_current 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 diagnose_current. 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.
diagnose_current 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.