io.github.tokenzero-ai/tokenzero
up checked
Unclaimed · Unverified
Agent searches it appeared in, last 30 days: 0. Run this server? Claim the listing: verified label, uptime alerts and analytics.
Publisher-provided title
TokenZero
Publisher-provided description
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
Summary by lookupd
Audits repos and prompts for LLM token waste, prices models for cost comparison, and reports workspace savings metrics.
Install
Claude Code, remote (streamable-http)
claude mcp add --transport http tokenzero https://tokenzero.sh/mcp
Codex, remote (streamable-http)
codex mcp add tokenzero --url https://tokenzero.sh/mcp
Cursor, remote (streamable-http) → .cursor/mcp.json
{
"mcpServers": {
"tokenzero": {
"url": "https://tokenzero.sh/mcp"
}
}
}Other clients: docs. Or tell your agent: Set up lookupd for me: read https://lookupd.com/agent.md and follow it.
Tools (6 tools)
Publisher-provided text
try_tokenzeroCall 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 formattaudit_repo_token_wasteNo 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, fronoptimize_prompt_payloadNo API key needed. Rewrite an OpenAI Chat/Responses or Anthropic Messages request body so its static prefix is provider-cacheable (Anthropic cache_control breakcalculate_model_arbitrageNo 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 modelsprovision_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-cliworkspace_metricsLive value scorecard for a TokenZero workspace: hard savings and net ROI per window, the four engines' contribution, speed, parity, availability and privacy pos
Details
- Version: 0.2.2
- Transports: streamable-http
- Uptime (7 days): 100%
- Median latency: 672 ms
- First indexed:
- Last seen in registry:
- Repository: https://github.com/tokenzero-ai/tokenzero
- Website: https://tokenzero.sh
Badge for your README
Shows this live status and links here; updates hourly.
[](https://lookupd.com/servers/io.github.tokenzero-ai/tokenzero)
- 62033 servers
- Last crawl: 2026-11-11T15:38:39.561Z
- API base:
https://api.lookupd.com - MCP URL:
https://api.lookupd.com/mcp