Tracks LLM API costs locally without proxying your traffic through a third party. Uses js-tiktoken to count tokens offline and stores session data in SQLite. Exposes tools to check current spend, get per-tool breakdowns, set budget alerts at custom thresholds, and suggest cheaper model alternatives based on task type. Works across Claude, OpenAI, and Gemini with a built-in pricing table you can override. Supports project tagging for chargeback reports and exports HTML summaries with charts. Reach for this when you need cost visibility without sending prompts to an external tracking service, or when you want routing suggestions baked into your agent workflow instead of bolted on afterward.
claude mcp add --transport stdio dbsectrainer-mcp-cost-tracker-router -- npx -y mcp-cost-tracker-router