Complete AI Training

MCP server · Analytics

LLM Token Tracker MCP server

by wn01011

See how many tokens your AI chats use and what they cost, right inside the chat.

Flow diagram: you ask your AI “How much has this chat cost so far?”, on your own computer the LLM Token Tracker MCP server works with your own computer, and you get back A short cost report in the chat.

This is a small helper that keeps an eye on how many tokens your AI conversations use and what that costs. It works with OpenAI, Claude, and Gemini models. It is handy if you pay for AI use yourself or need to show the cost to a client or your boss.

What is an MCP server? The 30-second version

On its own, your AI can only chat. An MCP server is a small helper program you connect once, and it gives your AI a new skill. This helper adds a running tally of token use and cost for your AI chats. So when you ask about spending, your AI can look it up through this helper and answer with real numbers.

What this MCP server does

You ask your AI something like how much this conversation has cost so far. Your AI passes the question to this helper. The helper looks at the token counts it has recorded and checks them against current prices for models from OpenAI, Claude, and Gemini. It adds everything up and sends back a short report. You see it right in the chat, with tokens used, tokens left, and a dollar amount.

Flow diagram: you ask your AI “How much has this chat cost so far?”, on your own computer the LLM Token Tracker MCP server works with your own computer, and you get back A short cost report in the chat. Click to zoom

What you can do with it

  • Check how many tokens the current chat has used
  • See the cost of the current conversation
  • Compare prices between models like GPT-4 and Claude
  • Track usage for a specific user or session
  • See a summary of spending today
  • Clear usage data for a user when you want a fresh start

Try asking your AI

  • “Calculate current session usage”
  • “Calculate current conversation cost”
  • “Compare costs between GPT-4 and Claude”
  • “Show my total spending today”

What it gives back to you

You get a short report in the chat. It shows tokens used and remaining, a simple progress bar, input and output token counts, and the cost in dollars. It can also break things down by model so you see which one used the most.

Before you start

What you need

  • The Claude desktop app (or another app that supports MCP servers)
  • Node.js installed on your computer

Good to know

It can clear usage data for a user, so be careful with the clear command if you want to keep your history.

Install it with your AI

Add LLM Token Tracker MCP server to your AI, no technical skills needed

You don't install anything by hand. You copy one prompt, paste it into an AI that can work on your computer, and it checks, installs and connects the server for you, asking you when it needs something.

Sign in to get the install prompt

Members get a ready-made prompt that lets the Claude desktop app check LLM Token Tracker MCP server, install it and connect it for them, step by step. You don't need any technical skills: you copy, paste and answer a few questions. Your connected AI can also find and install any of the 4,066 MCP servers here for you.

Sign in Become a member

Who it's for

Anyone who pays for AI API use and wants to keep an eye on spending, like freelancers, small teams, and people building AI features.