Your MCP server's tool calls are silently burning money. Here's a 40-line budget guard.

A developer published a 40-line JavaScript budget guard for MCP servers that caps per-agent tool calls by time and token budget, addressing runaway LLM tool invocations that the author says can turn a $12 job into $47. The ToolCallBudgetGuard class tracks time used, tokens consumed and cost per agent, emits budgetExceeded and callRecorded events, and wraps client.callTool calls so agents are blocked once limits are hit.

Your MCP server's tool calls are silently burning money. Here's a 40-line budget guard. You have 3 agents running in parallel, each calling the same expensive LLM tool 50 times per minute. The first agent finishes its batch and stops. The second and third agents keep calling until their 10-minute time budget expires. By then you've spent $47 on a job that should have cost $12. This happens because MCP tool calls are fire-and-forget: you send the request, you get a result, and you never track how much you've spent. No per-call budget, no time limit, no per-agent cap. Here's a 40-line budget guard that stops runaway tool calls in their tracks. An MCP server exposes a tool like this: { "name": "llm generate", "description": "Generate text using an LLM", "inputSchema": { "type": "object", "properties": { "prompt": { "type": "string" }, "model": { "type": "string", "enum": "gpt-4", "claude-3-5-sonnet" } } } } Your agent calls it like this: js const result = await client.callTool { name: "llm generate", arguments: { prompt: "Write a Python script to..." } } ; No budget, no time limit, no per-agent cap. If the agent loops 100 times, you pay for 100 calls. Wrap the tool call in a budget guard that tracks: js // budget-guard.js import { EventEmitter } from "events"; class ToolCallBudgetGuard { constructor options = {} { this.timeBudget = options.timeBudget || 10 60 1000; // 10 minutes this.tokenBudget = options.tokenBudget || 10 000; this.costPerToken = options.costPerToken || 0.00003; // GPT-4 ~$3/1M tokens this.budgets = new Map ; // agentId - { timeUsed, tokensUsed, startTime } this.emitter = new EventEmitter ; } // Get or create a budget for an agent getBudget agentId { if this.budgets.has agentId { this.budgets.set agentId, { timeUsed: 0, tokensUsed: 0, startTime: Date.now } ; } return this.budgets.get agentId ; } // Check if a tool call is allowed canCall agentId, estimatedTokens = 0 { const budget = this.getBudget agentId ; const timeUsed = Date.now - budget.startTime; const tokensUsed = budget.tokensUsed + estimatedTokens; const timeExceeded = timeUsed this.timeBudget; const tokensExceeded = tokensUsed this.tokenBudget; if timeExceeded || tokensExceeded { this.emitter.emit "budgetExceeded", { agentId, reason: timeExceeded ? "time" : "tokens", timeUsed, tokensUsed } ; return false; } return true; } // Record a successful tool call recordCall agentId, tokens = 0, cost = 0 { const budget = this.getBudget agentId ; budget.timeUsed = Date.now - budget.startTime; budget.tokensUsed += tokens; budget.cost += cost; this.emitter.emit "callRecorded", { agentId, tokens, cost, timeUsed: budget.timeUsed, tokensUsed: budget.tokensUsed } ; } // Get current budget usage getUsage agentId { const budget = this.budgets.get agentId ; if budget return null; return { timeUsed: Date.now - budget.startTime, tokensUsed: budget.tokensUsed, cost: budget.cost }; } } export default ToolCallBudgetGuard; python import ToolCallBudgetGuard from "./budget-guard.js"; const guard = new ToolCallBudgetGuard { timeBudget: 10 60 1000, // 10 minutes tokenBudget: 10 000, costPerToken: 0.00003 // GPT-4 } ; // Listen for budget exceeded events guard.on "budgetExceeded", { agentId, reason, timeUsed, tokensUsed } = { console.error ${agentId} Budget exceeded: ${reason} ; console.error Time used: ${Math.round timeUsed / 1000 }s ; console.error Tokens used: ${tokensUsed} ; } ; // Wrap your tool call async function callLLM agentId, prompt, model = "gpt-4" { // Estimate tokens simplified: 4 chars per token for English const estimatedTokens = Math.ceil prompt.length / 4 ; // Check budget before calling if guard.canCall agentId, estimatedTokens { throw new Error Tool call blocked: budget exceeded for ${agentId} ; } // Call the LLM const result = await openai.chat.completions.create { model, messages: { role: "user", content: prompt } } ; // Record the call guard.recordCall agentId, result.usage.total tokens, result.usage.total tokens guard.costPerToken ; return result.choices 0 .message.content; } // Use it in your agent const agent1 = callLLM "agent-1", "Write a Python script..." ; const agent2 = callLLM "agent-2", "Write a Python script..." ; const agent3 = callLLM "agent-3", "Write a Python script..." ; length / 4 llm generate separately from others. Runaway tool calls are a silent budget killer. A 40-line guard stops them before they burn you. This article is a teaching piece. For a production-ready MCP tool-call budgeting pack, see the linked resources above.