Break down usage and cost by AI model over a time period.
AI agents call usage_by_model to retrieve information from Langfuse MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs aggregation and reporting of historical usage/cost metrics—a purely informational query with no side effects. While cost data may be business-sensitive, disclosure alone does not constitute Write, Execute, Destructive, or Financial action. The tool does not move money, execute code, modify records, or delete data; it merely retrieves and breaks down existing analytics.
From the tool's definition Tool retrieves analytics data ('usage and cost by AI model') without modifying, deleting, or executing operations. Server description emphasizes 'querying' and 'analysis' of metrics and usage data.
Attacks that exploit this kind of access
Break down usage and cost by AI model over a time period. It is categorised as a Read tool in the Langfuse MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Langfuse MCP Server MCP server in PolicyLayer and add a rule for usage_by_model: 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 Langfuse MCP Server. Nothing to install.
usage_by_model 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 usage_by_model 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 usage_by_model. 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.
usage_by_model is provided by the Langfuse MCP Server MCP server (therealsachin/langfuse-mcp). 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 →