Exposes tools to query and analyze energy monitoring sessions stored in CSV files, enabling users to get consumption stats, compare sessions, and view historical data through natural language in Claude Desktop.
Analyzes Claude Code session token usage and cost locally — where spend actually lands across cache-read, cache-write and output, and what is consuming the context window. Read-only and offline: it parses your own session files and exposes analyze_claude_cost, get_cost_benchmark and tokenscope_share_summary.
Local-first dashboard + MCP server that parses Claude Code and Codex JSONL files into a SQLite cost / token tracker. Per-MCP and per-tool breakdown, session drill-down, dedup by request_id; never talks to vendor APIs
Surface Claude Code token usage, estimated cost, and plan-limit status in any MCP client. Enables agents to query usage data from local logs and Anthropic API.
Enables querying and analyzing Claude Desktop/Code conversation history across all users on a machine, including conversation search, token usage statistics, model/tool insights, and opening a web dashboard for detailed visualization.
