# Tokenzero Ai Tokenzero MCP server

Source: https://glimind.com/server/mcp-registry%2Fio.github.tokenzero-ai%2Ftokenzero
Registry id: `mcp-registry/io.github.tokenzero-ai/tokenzero`
Status: live (checked 2026-11-22T18:53:32.558Z)

## Measurements (30 days)

- Uptime: 100%
- Checks: 735
- Outages (90 days): 0

## Install

```json
{
  "mcpServers": {
    "tokenzero-ai-tokenzero-mcp-server": {
      "type": "http",
      "url": "https://tokenzero.sh/mcp"
    }
  }
}
```

Claude Code:

```sh
claude mcp add --transport http tokenzero-ai-tokenzero-mcp-server https://tokenzero.sh/mcp
```

## Tools (6)

- `audit_repo_token_waste`: No API key needed. Static-analyze a public GitHub repo (e.g. {"repo": "owner/name"}) or a set of source files for LLM token waste: uncached static prompts, fron
- `calculate_model_arbitrage`: No API key needed; only `model` is required (e.g. {"model": "gpt-6.1-sol"}, defaults 2,000 tokens in and 400 out). Price a workload at list prices across models
- `optimize_prompt_payload`: No API key needed. Rewrite an OpenAI Chat/Responses or Anthropic Messages request body so its static prefix is provider-cacheable (Anthropic cache_control break
- `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-cli
- `try_tokenzero`: Call this first: no API key, no signup, no setup. Shows what TokenZero would do to one of your LLM calls: it runs the four savings engines (prompt-cache formatt
- `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 pos

Measured by Glimind (https://glimind.com): MCP handshake + tool list only, no tool is ever called. CC BY 4.0.
