Tokmeter — AI Agent Usage & Cost MCP server

Read from the package source without running it. The installed server may list more.

• drishti_anomaly

  Detect unusual spending patterns and anomalies in token usage.

• drishti_backups

  List available cleanup backups with metadata (date, size, providers, projects).

• drishti_budget

  Monitor spending against a budget with visual progress bars and alerts.

• drishti_budget_alert

  Proactive budget monitoring with configurable daily/weekly/monthly thresholds.

• drishti_cache_efficiency

  Analyze cache hit/miss patterns across sessions. Shows overall cache hit rate, dollar savings from caching,

• drishti_cleanup_executewrite action

  DESTRUCTIVE: Permanently delete session data matching the given filters.

• drishti_cleanup_preview

  Preview what session data would be deleted for the given filters.

• drishti_compare

  Compare two or more models or providers side-by-side on cost, tokens, efficiency, and usage metrics.

• drishti_cost_optimization_tips

  Analyze usage patterns and provide actionable cost optimization recommendations.

• drishti_digest

  Generate a concise natural language summary of token usage — like a daily/weekly briefing.

• drishti_efficiency

  Analyze cache hit rates, reasoning token ratios, input/output efficiency, and cost-per-token metrics.

• drishti_export

  Export token usage data as JSON, CSV, or Markdown.

• drishti_forecast

  Project future AI token costs based on historical burn rates.

• drishti_heatmap

  Visualize activity patterns as a heatmap — see which hours of the day and days of the week have the heaviest usage.

• drishti_leaderboard

  Rank models and providers by various metrics: total cost, cost-efficiency (cost per 1M tokens),

• drishti_model_advisor

  Compare what you actually spent vs what cheaper models would have cost.

• drishti_models

  Detailed per-model cost and token breakdown with visual bar charts.

• drishti_projects

  Show per-project token usage breakdown — cost, tokens, active days, models used, and date range.

• drishti_providers

  Compare token usage across providers (Claude Code, Cursor, Codex, Gemini, etc.).

• drishti_pulse

  Get a quick pulse-check snapshot of token usage — total cost, tokens, active models, projects, and providers.

• drishti_restore

  Restore session data from a cleanup backup. Requires confirm='RESTORE' as a safety guard.

• drishti_search

  Flexible search across all token usage records with filtering by model, provider, project, date range, and cost thresholds.

• drishti_streaks

  Analyze your AI coding habits — active day streaks, weekend vs weekday usage, session frequency,

• drishti_timeline

  Show a day-by-day timeline of token usage with sparkline trends and daily cost/token breakdowns.

• Code scan55 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 0 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Tokmeter — AI Agent Usage & Cost: common questions

Is Tokmeter — AI Agent Usage & Cost MCP server safe?

Yes, by our scan: it is graded A (92/100). Read the Tokmeter — AI Agent Usage & Cost safety report

How do I install Tokmeter — AI Agent Usage & Cost?

It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.

Does Tokmeter — AI Agent Usage & Cost need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Tokmeter — AI Agent Usage & Cost maintained?

The last commit was in the last day (2026-09-19). The latest release is v1.12.0.

What can I use instead of Tokmeter — AI Agent Usage & Cost?

Servers from other publishers that do the same job: llmtrim MCP server, Async Parallel Antigravity for Codex & Claude Code MCP server and mcptoon MCP server. Compare all Tokmeter — AI Agent Usage & Cost alternatives.