openclaw-cost-tracker-mcp
JSON →MCP server for AI agent token-cost telemetry + quota-window awareness across Anthropic, OpenAI, Gemini, Ollama, AWS Bedrock. Per-agent attribution, spend-spike detection, 429-prediction tools.
Install
pip install openclaw-cost-tracker-mcp Tools · 6
- cost_overview Get a summary of total spend over a specified time period, broken down by provider and agent.
- top_cost_drivers Identify the top cost-driving agents or models over a specified time period.
- find_cost_anomalies Detect spend spikes per agent using median-based anomaly detection.
- model_routing_recommendations Suggest cheaper model routing alternatives with estimated 30-day savings.
- predict_429_in_window Predict if a provider rate limit (429) will be hit before the current window resets, based on burn rate.
- recommend_throttle_target Recommend a safe burn rate to avoid hitting provider rate limits, given a target buffer percentage.