Skip to content
Migrate your GPTCheck my InvokeRank
Official MCP RegistryListed

TokenZero

Part ofTokenZeroMCP server

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

First seen 26 Oct 2026. Evidence as of 28 Oct 2026.

5
Tools
From an anonymous probe
1
Source listings
Each with its own history
13
Recorded changes
Since first seen

Tools

ToolDescriptionBehaviour
audit_repo_token_wasteStatic-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.Changes data
calculate_model_arbitragePrice 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 2026-10-27.Read-only
optimize_prompt_payloadRewrite 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.Read-only
provision_workspaceCreate 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.Changes data
workspace_metricsLive 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.Read-only

Change history

  1. calculate_model_arbitrage: description changed (+"2026-10-27." -"2026-10-26.")
  2. workspace_metrics: title changed
  3. workspace_metrics: annotations changed
  4. provision_workspace: title changed
  5. provision_workspace: annotations changed
  6. optimize_prompt_payload: title changed
  7. optimize_prompt_payload: annotations changed
  8. calculate_model_arbitrage: title changed
  9. calculate_model_arbitrage: annotations changed
  10. audit_repo_token_waste: title changed
  11. audit_repo_token_waste: annotations changed
  12. server instructions changed (+"gateway: point" +"OpenAI, Anthropic or Gemini" +"(your provider key passes through; nothing is stored or resold) and every call gets prompt-cache formatting, an edge response cache, optional cascade routing and an Ed25519-signed savings receipt. Tools:")
  13. Listed (registry)
Source listings
SourceListingFirst seenLast seenVersions
Official MCP Registryio.github.tokenzero-ai/tokenzero26 Oct 202628 Oct 20261