Claude Token Analyzer

Created By
li1951112 months ago
Diagnoses token waste in Claude Code sessions. Detects 6 types of statistical anomalies with severity scoring. Fully local — parses ~/.claude JSONL files into SQLite, nothing leaves your machine. Plugin-native: one command install, then just ask "cta".
Overview

claude-token-analyzer

Diagnoses token waste in Claude Code sessions. Detects 6 types of statistical anomalies with severity scoring.

Features

  • 6 Anomaly Types: Token explosion, low cache hit, cost inefficient, extended session, repetitive errors, unusual model distribution
  • Cost Audit: Per-project, per-model cost breakdown with trend analysis
  • Fully Local: Parses ~/.claude JSONL files into SQLite — nothing leaves your machine
  • Plugin-Native: One command install, natural language interface

Install

claude plugin install claude-token-analyzer

Usage

Just ask Claude Code naturally:

  • "Scan my sessions for anomalies"
  • "How much did I spend this month?"
  • "Show usage trends for the past week"

MCP Tools

ToolDescription
sync_dbSync JSONL session logs to SQLite
anomaly_scanDetect 6 types of usage anomalies
cost_reportMonthly cost breakdown by project/model
trend_reportDaily/weekly/monthly usage trends
analyze_sessionDeep-dive into a single session
analyze_projectProject-level efficiency analysis
analyze_globalCross-project usage overview

License

MIT

Server Config

{
  "mcpServers": {
    "claude-token-analyzer": {
      "command": "cta-mcp-server",
      "args": []
    }
  }
}
Project Info
Created At
2 months ago
Updated At
2 months ago
Author Name
li195111
Star
-
Language
-
License
-
Category

Recommend Servers

View All
Crevio

a day ago
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)

19 hours ago