track_usage
Monitor and record token consumption for AI API calls from OpenAI and Anthropic models to track usage patterns and manage costs.
Instructions
Track token usage for an AI API call
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| input_tokens | Yes | Input tokens used | |
| model | Yes | Model name | |
| output_tokens | Yes | Output tokens used | |
| provider | Yes | AI provider | |
| user_id | No | Optional user ID |
Implementation Reference
- src/mcp-server.ts:178-204 (handler)The main handler function that executes the track_usage tool logic. It tracks token usage via the TokenTracker, calculates costs, and returns a formatted response.private trackUsage(args: any) { const { provider, model, input_tokens, output_tokens, user_id = 'current-session' } = args; const trackingId = this.tracker.startTracking(user_id); this.tracker.endTracking(trackingId, { provider: provider as 'openai' | 'anthropic' | 'gemini', model, inputTokens: input_tokens, outputTokens: output_tokens, totalTokens: input_tokens + output_tokens }); const usage = this.tracker.getUserUsage(user_id); const totalTokens = input_tokens + output_tokens; const cost = usage?.totalCost || 0; return { content: [ { type: 'text', text: `✅ Tracked ${totalTokens.toLocaleString()} tokens for ${model}\n` + `💰 Session Cost: ${formatCost(cost)}\n` + `📊 Total: ${usage?.totalTokens.toLocaleString() || 0} tokens` } ] }; }
- src/mcp-server.ts:53-79 (schema)The input schema definition for the track_usage tool, specifying parameters like provider, model, input/output tokens.inputSchema: { type: 'object', properties: { provider: { type: 'string', enum: ['openai', 'anthropic', 'gemini'], description: 'AI provider' }, model: { type: 'string', description: 'Model name' }, input_tokens: { type: 'number', description: 'Input tokens used' }, output_tokens: { type: 'number', description: 'Output tokens used' }, user_id: { type: 'string', description: 'Optional user ID' } }, required: ['provider', 'model', 'input_tokens', 'output_tokens'] }
- src/mcp-server.ts:50-80 (registration)The tool registration in the ListTools response, including name, description, and schema.{ name: 'track_usage', description: 'Track token usage for an AI API call', inputSchema: { type: 'object', properties: { provider: { type: 'string', enum: ['openai', 'anthropic', 'gemini'], description: 'AI provider' }, model: { type: 'string', description: 'Model name' }, input_tokens: { type: 'number', description: 'Input tokens used' }, output_tokens: { type: 'number', description: 'Output tokens used' }, user_id: { type: 'string', description: 'Optional user ID' } }, required: ['provider', 'model', 'input_tokens', 'output_tokens'] } },
- src/mcp-server.ts:160-161 (registration)The dispatch case in the CallToolRequest handler that routes to the trackUsage method.case 'track_usage': return this.trackUsage(request.params.arguments);