Query aggregated metrics (costs, tokens, counts) with flexible filtering and dimensions.
AI agents call get_metrics 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.
While the tool retrieves cost and usage metrics which could be considered sensitive business intelligence data (elevating severity to medium rather than low), it performs no modifications, deletions, or external state changes. The operation is purely informational.
From the tool's definition Tool name 'get_metrics' with description 'Query aggregated metrics (costs, tokens, counts)' indicates data retrieval.
Attacks that exploit this kind of access
Query aggregated metrics (costs, tokens, counts) with flexible filtering and dimensions. 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 get_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 Server. Nothing to install.
get_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_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_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_metrics 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 →