claudestat — Claude Code & OpenCode usage tracker with MCP

Created By
DeibyGS2 days ago
Local daemon that tracks Claude Code and OpenCode sessions in real-time. Exposes an MCP server so Claude can query its own usage mid-session: quota status, session cost, top tools, weekly insights, burn rate, and model breakdown. No cloud, no accounts — everythin stays on disk.
Overview

claudestat MCP Server

claudestat includes an MCP (Model Context Protocol) server that lets Claude Code query its own usage stats — Claude can tell you its quota, session cost, and top tools in real time.

Register with Claude Code

claude mcp add claudestat -s user -- claudestat-mcp

Once registered, ask Claude things like:

  • "What's my current quota status?"
  • "Show me my latest session cost"
  • "What are my top 5 tools by cost this week?"
  • "Give me usage insights for the last 14 days"
  • "Break down my usage by model"

Tools

ToolDescription
get_quota_status5h cycle usage %, plan, weekly hours, burn rate (with on-demand API refresh + disk cache)
get_current_sessionLatest session: cost, tokens, efficiency, loops
get_session_statsAggregated stats for N days
get_top_toolsTop 10 tools by cost/count/duration (default 30 days)
get_usage_insightsDeep insights: cost per project, cache savings, efficiency trend, peak hours, model breakdown
get_model_breakdownCost and session count broken down by Claude model (Sonnet, Haiku, Opus)
get_weekly_insightWeekly summary with actionable tip

Zero extra dependencies — stdio JSON-RPC. Works without the daemon running (reads SQLite directly), but will warn you to start it if it's not active.

claudestat MCP demo

Server Config

{
  "mcpServers": {
    "claudestat": {
      "command": "claudestat-mcp",
      "args": []
    }
  }
}
Project Info
Created At
2 days ago
Updated At
2 days ago
Author Name
DeibyGS
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Bring your real authenticated browser session to AI coding agents. Local-first MCP server + Chrome MV3 extension. No cloud. No telemetry.
@Cubenest

peek records the user's actual logged-in browser (DOM via rrweb, console events, network metadata, optional response bodies via opt-in Deep capture) through a Chrome MV3 extension. The extension ships events through a native-messaging stdio bridge to a local MCP server (peek-mcp), which persists them to a SQLite database at ~/.peek/sessions.db. AI coding agents (Claude Code, Cursor, Cline, Windsurf) read sessions from the database via 10 MCP tools: Tool What it does list_recent_sessions List recently recorded sessions (id, origin, ts, event count). get_session_summary LLM-readable narrative summary of a session. get_session_console_errors Console errors recorded in a session. get_session_network_errors Failed/notable network requests in a session. get_user_action_before_error Last N user actions before a console error. generate_playwright_repro Generate a runnable Playwright test from a session. get_dom_snapshot Reconstruct the DOM at a given timestamp. query_dom_history Timeline of attribute/text changes for a selector. request_authorization Side-panel consent for write actions (Level 3). execute_action Dispatch a UI action (gated by permission level + destructive blocklist). Why local-first matters Every other "browser session for AI" tool ships to a vendor cloud. peek's SQLite + extension live on the user's machine — no remote endpoints, no telemetry. The privacy policy (docs/peek/PRIVACY_POLICY.md) is the source of truth. Install # 1. Add the MCP server to Claude Code claude mcp add peek -- npx -y @peekdev/mcp # 2. Install the Chrome extension from the Chrome Web Store # (link added once the CWS listing is approved)

a day ago