Query Langfuse cost, token, latency, and usage analytics via the Metrics API.
AI agents call get_cost_metrics to retrieve information from Langfuse Mcp Python without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and queries existing metrics and analytics data (cost, tokens, latency, usage) from Langfuse without modifying, deleting, or executing any operations. The financial term 'cost' refers to querying cost data, not moving money or creating financial obligations. Classification as Read is appropriate for a query-only analytics retrieval tool.
From the tool's definition Tool description states 'Query Langfuse cost, token, latency, and usage analytics' - the verb 'Query' and action of retrieving analytics data indicates data retrieval with no side effects.
Attacks that exploit this kind of access
Query Langfuse cost, token, latency, and usage analytics via the Metrics API. It is categorised as a Read tool in the Langfuse Mcp Python MCP Server, which means it retrieves data without modifying state.
Register the Langfuse Mcp Python MCP server in PolicyLayer and add a rule for get_cost_metrics: 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 Python. Nothing to install.
get_cost_metrics 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 get_cost_metrics 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 get_cost_metrics. 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.
get_cost_metrics is provided by the Langfuse Mcp Python MCP server (log-logn/langfuse-mcp-python). 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 →