Find the most expensive traces by cost over a time period.
AI agents call top_expensive_traces 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 and aggregates cost metrics from historical trace data to identify expensive operations. It is purely analytical with no capacity to modify data, execute operations, or trigger external actions.
From the tool's definition Tool name 'top_expensive_traces' and description 'Find the most expensive traces by cost over a time period' indicate a query/retrieval operation that analyzes existing analytics data without modifying, executing code, or causing side effects.
Attacks that exploit this kind of access
Find the most expensive traces by cost 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 top_expensive_traces: 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.
top_expensive_traces 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 top_expensive_traces 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 top_expensive_traces. 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.
top_expensive_traces 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 →