MCP server · Analytics

Metrx MCP server

Lets your AI track what your AI agents cost, find waste, and suggest cheaper models.

Analytics For it and development Monitoring

Metrx is a helper that lets your AI assistant look at how much money your AI agents are spending. You can ask plain questions like how much did I spend this week, and it pulls the numbers together for you. It is handy if you run AI agents at work and want to know where the money goes.

What is an MCP server? The 30-second version

On its own, your AI can only chat with you. An MCP server is a small helper program that gives your AI a new skill or a connection to another service. This one connects your AI to Metrx, a service that tracks AI agent costs. Once connected, your AI can look up your spending, check budgets, and suggest cheaper options when you ask.

What this MCP server does

You ask your AI a question about your AI agents, like how much you spent this week. Your AI sends that request to this helper program. The helper talks to Metrx, which holds your cost data. Metrx sends back numbers, lists, and suggestions, and your AI shows them to you in the chat. You can also ask it to set a budget or start a test comparing two models.

Flow diagram: you ask your AI “What did my AI agents cost this week?”, the Metrx MCP server connects it to Metrx, and you get back plain answers in your chat.

Click to zoom

What you can do with it

See how much your AI agents spent this week or month
List all your agents with their costs and health
Get suggestions for cheaper models that do the same job
Set a spending budget and pause an agent when it hits the limit
Run a scan that looks for wasted money across your agents
Start a test comparing two models side by side
Generate a report that shows the return on your AI spending

Try asking your AI

“What was my AI cost this week?”
“Am I overpaying for my agents?”
“Set a monthly budget of 500 dollars for my support agent”
“Run a cost leak scan on all my agents”

What it gives back to you

You get back plain answers in the chat: totals, lists of agents with their costs, comparisons of model prices, and suggestions for saving money. Budget checks show how much you have spent against your limit. Reports come back as summaries you can read or share. Some actions, like setting a budget or starting a test, will tell you they were done.

Before you start

What you need

A free Metrx account and API key from app.metrxbot.com/sign-up (an API key is a kind of password for apps)
Node.js installed on your computer if you run it locally
An MCP-compatible AI app like Claude Desktop, Cursor, or Windsurf

Good to know

This can change your setup: it can set budgets, pause agents, and start or stop model tests, so review what it is about to do before you say yes.

Install it with your AI

Add Metrx 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 Metrx 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.