Official MCP RegistryListed

TokenZero

LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.

First seen 26 Oct 2026. Evidence as of 26 Oct 2026.

Tools

From an anonymous probe

Source listings

Each with its own history

Recorded changes

Since first seen

Tools

Tool	Description	Behaviour
audit_repo_token_waste	Static-analyze a public GitHub repo (owner/name) or a set of source files for LLM token waste: uncached static prompts, frontier models on extraction tasks, hot loops, non-deterministic repeat calls. Returns findings with fixes and an estimated recoverable percentage.	Not declared
calculate_model_arbitrage	Price a workload at list prices across models: cost per request and per month for the requested model, its cheaper sibling, and the effect of prompt caching. Pricing table version 2026-10-26.	Not declared
optimize_prompt_payload	Rewrite an OpenAI Chat/Responses or Anthropic Messages request body so its static prefix is provider-cacheable (Anthropic cache_control breakpoints, OpenAI prompt_cache_key). Returns the optimized body, what changed, the token profile and the projected per-request saving. Never changes the tokens the model sees.	Not declared
provision_workspace	Create a TokenZero workspace and key with no form. Returns the key once, the base URLs that route through it (OPENAI_BASE_URL / ANTHROPIC_BASE_URL), the one-click dashboard link and the badge URL. Free up to the monthly free tier; nothing is billed.	Not declared
workspace_metrics	Live value scorecard for a TokenZero workspace: hard savings and net ROI per window, the four engines' contribution, speed, parity, availability and privacy posture, per-model breakdown and one-click recommendations. Needs the workspace key (tz_live_…); pass demo: true for a labelled sample.	Not declared

Change history

26 Oct 2026, 07:08 UTC
Listed (registry)

Source listings
Source	Listing	First seen	Last seen	Versions
Official MCP Registry	sh.tokenzero/mcp	26 Oct 2026	26 Oct 2026	1