MCP server for deterministic, zero-dependency context-window math, enabling token estimation, text truncation, and budget reporting without a tokenizer.
Counts LLM prompt tokens and estimates API costs across OpenAI and Anthropic models directly inside MCP-compatible chat clients. Supports exact tokenization for OpenAI models and fallback approximation for Claude when no API key is present.
Local-first MCP server that watches your coding sessions and injects a compact summary at the start of each new session. 85.6% token reduction, SQLite storage, no cloud. Works with Claude Code, Cursor, Cline, and Windsurf.
Enables local-first tracking of AI token usage and costs from Claude Code and OpenCode, answering queries about tokens, models, sessions, and cost through MCP tools and a CLI, with no network calls.