Analyze usage and cost by service/feature tag over a time period.
AI agents call usage_by_service 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 retrieves usage and cost metrics from Langfuse analytics. While it accesses potentially sensitive business intelligence (cost and usage data), it does not modify data, execute code, delete records, or move money.
From the tool's definition Tool is described as 'Analyze usage and cost by service/feature tag over a time period' — it retrieves and queries analytics data without modifying, deleting, or executing external operations. It is a read-only analytical query.
Attacks that exploit this kind of access
Analyze usage and cost by service/feature tag 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_service: 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_service 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_service 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_service. 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_service 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 →