Claude Usage Mcp

Name: Claude Usage Mcp
Author: Orellius

@Orellius

About Claude Usage Mcp

MCP server for Claude Pro/Max subscription usage — session limits, weekly limits, per-model breakdown, extra credits. Zero config, reads your existing OAuth token.

#cli #oauth #subscription #typescript #mcp #rate-limits #max #usage #developer-tools #statusline #pro #claude #anthropic #model-context-protocol #claude-code

Basic information

Config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "claudeusage": {
      "command": "node",
      "args": [
        "/absolute/path/to/claudeusage-mcp/dist/index.js"
      ]
    }
  }
}

Tools

Full dashboard — session, weekly, per-model, extra usage with progress bars

Current 5-hour session window only

7-day limits with per-model breakdown (All, Opus, Sonnet)

Am I about to be rate-limited? Returns LOW / MODERATE / HIGH / RATE LIMITED

Overview

What is Claude Usage Mcp?

Claude Usage Mcp is an MCP server that gives real‑time visibility into your Claude Pro/Max subscription usage directly inside Claude Code. It reads the OAuth token already stored on your machine and calls Anthropic’s usage endpoint—no API keys, scraping, or browser automation required.

How to use Claude Usage Mcp?

Clone the repository, run npm install && npm run build, then add the server via claude mcp add claudeusage -- node $(pwd)/dist/index.js or manually in your MCP config. After restarting Claude Code, ask “what’s my usage?” or type /usage. Optional statusline integration adds a persistent usage line.

Key features of Claude Usage Mcp

Reads OAuth credentials from macOS Keychain or ~/.claude/.credentials.json
Provides four MCP tools: get_usage, get_session_usage, get_weekly_limits, check_rate_status
Caches responses for 60 seconds with stale‑data fallback on rate limits
Color‑coded progress bars (green/orange/red) for usage levels
Statusline script shows usage in the Claude Code status bar
Works on macOS and Linux with Node.js 18+

Use cases of Claude Usage Mcp

Monitor current 5‑hour session window utilization and reset countdown
Check weekly usage across all models and per‑model (Opus, Sonnet)
See if you are approaching or currently rate‑limited
Track extra usage credits and monthly limits
Get all usage data without leaving the terminal or opening a browser

FAQ from Claude Usage Mcp

How does Claude Usage Mcp authenticate?

It uses the same OAuth token that Claude Code creates when you sign in with a Pro/Max subscription. No API keys, environment variables, or .env files are required.

What are the runtime requirements?

Node.js 18 or later, macOS or Linux, and a Claude Code session logged in with a Pro or Max subscription.

Where does my usage data come from?

The server calls GET https://api.anthropic.com/api/oauth/usage with the stored OAuth token. It caches the response for 60 seconds and serves stale data if the endpoint rate‑limits the request.

Does Claude Usage Mcp work with API keys?

No. This server is for Pro/Max subscribers only. API users should use the official Usage and Cost API instead.

What happens if my token expires?

Restart Claude Code to trigger a fresh OAuth login. If you previously used claude setup-token or /login, the token may have the wrong scopes; delete the credentials file and restart Claude Code.

Comments

More AI & Agents MCP servers

MCP Claude Code

SDGLBL

MCP implementation of Claude Code capabilities and more

302

MCP Server - Remote MacOs Use

baryhuang

The only general AI agent that does NOT requires extra API key, giving you full control on your local and remote MacOs from Claude Desktop App

487

MCP Client for Ollama (ollmcp)

jonigl

Harness the power of local LLMs with this TUI MCP Client for Ollama. Featuring all core MCP primitives (tools, prompts, resources), agent mode, multi-server, model switching, streaming responses, human-in-the-loop, thinking mode, model params config, system prompts, and saved pre

768