LLM Usage MCP Server

by zhaoyue722 Your server? Claim it

local only

LLM Usage runs on your own machine — the client starts it, so there is no endpoint to ping. 80 installs a week from pypi. Last commit 17 Sep 2026.

Local-first, multi-provider tool that captures LLM API spend and exposes it to coding agents via MCP

Installs per day peak 28 · avg 14 · -23% w/w

a month agotoday

Installs / week

pypi · llm-usage-mcp

Stars

0 open issues

17 Sep 2026

Last commit

0 releases in 90 days

MIT

License

Python

Nothing serious here today

Today is the operative word: we check LLM Usage every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add llm-usage-mcp -- uvx llm-usage-mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "llm-usage-mcp": {
      "args": [
        "llm-usage-mcp"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.llm-usage-mcp]
command = "uvx"
args = ["llm-usage-mcp"]

.cursor/mcp.json

{
  "mcpServers": {
    "llm-usage-mcp": {
      "args": [
        "llm-usage-mcp"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "llm-usage-mcp": {
      "args": [
        "llm-usage-mcp"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to LLM Usage

same job, measured the same way

MCP Context Server

by alex-feel

An MCP server that provides persistent multimodal context storage for LLM agents.

472 installs/wk local only

Architecture Pattern MCP

by olk

MCP server that provides architecture design expertise to AI coding agents

34 installs/wk local only

Dev953

by gru-953

dev953 method companion: exposes its multi-agent coding method as callable MCP tools.

local only

Vibemovie

by pooriaarab

Turns an agent coding session into a short recap video. Local-first.

51 installs/wk local only

Datacron

by vblackjack

Local-first MCP server that exposes a Markdown vault through MCP.

1 802 installs/wk local only

Prophetkey MCP

by lbz558

ProphetKey MCP bridge - encrypted local-first API key vault for AI agents, keys never exposed

42 installs/wk local only

4q Tokenz

by steveweltman

Intelligent MCP proxy that reduces token usage by exposing only mcp_search and mcp_call.

62 installs/wk local only

MCP Light Memory

by peterpirog

Local-first persistent memory for coding agents and MCP clients.

local only

LLM Usage — questions

Answers built from our own checks of this server.

Why is there no uptime for LLM Usage?

LLM Usage runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package llm-usage-mcp was installed 80 times last week.

How do I connect LLM Usage?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls llm-usage-mcp straight from pypi; nothing to host, nothing to sign up for.

How many people use LLM Usage?

The pypi package llm-usage-mcp was installed 80 times in the last week. Week over week that is -23%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is LLM Usage open source?

Yes — it is published under the MIT licence, written in Python and 4 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.