$ loading_
Track AI usage, costs, logs, and debug model interactions across apps.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "ai-usage-metrics-mcp" yet — see the docs or source repo.
Summarize AI model calls, token usage, and costs for the past 30 days across applications. Break down by app, model, and team, and highlight the top 5 cost drivers.
A usage and cost report grouped by app, model, and team, with the highest cost sources highlighted.
Analyze AI request logs from the past week to identify peak hours, failure rate changes, average latency, and usage trends by model across business scenarios.
A usage trend analysis summary including peak periods, anomalies, and key performance metric changes.
Use structured logs to investigate abnormal AI responses in an application. Identify failed requests, related context, prompts, model outputs, and error codes, then summarize likely causes.
A debugging report with failed request details, likely causes, and troubleshooting recommendations.
Build, debug, and manage software tasks with natural language across LLMs.
Query normalized usage, cost, and dashboard data across OpenAI and Anthropic.
Connect to the mcp API via MCP to extend AI tool capabilities.
View tenant-scoped AI credit usage data for admin users.
Query Prometheus metrics with PromQL and analyze monitoring trends and anomalies.
Give AI read-only logs to debug Linux servers safely without shell access.