Get the current session's token count and context window usage percentage. Fast check — reads only the tail of the session file.
AI agents call estimate_tokens 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 performs a query operation to retrieve session statistics and usage data. It explicitly reads data without creating, modifying, deleting, or executing external operations. The mention of 'Fast check — reads only' confirms no state changes occur. Blast radius is minimal as misuse would only expose session metadata.
From the tool's definition Tool description states: 'Get the current session's token count and context window usage percentage' and 'reads only the tail of the session file.' These are read-only operations that retrieve session metrics without modification or side effects.
Documented attack patterns abuse exactly the kind of access estimate_tokens 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 estimate_tokens:
{
"version": "1",
"default": "deny",
"tools": {
"estimate_tokens": {}
}
}estimate_tokens 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.
Get the current session's token count and context window usage percentage. Fast check — reads only the tail of the session file. 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 estimate_tokens: 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.
estimate_tokens 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 estimate_tokens 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 estimate_tokens. 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.
estimate_tokens 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.