io.github.tokenzero-ai由 GitHub 账号 tokenzero-ai 发布v0.2.2更新于 Oct 26, 2026
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
发布方自己的服务：TokenZero
TokenZero 审计代码中的 LLM token 浪费、改写请求体以启用提示缓存、比价不同模型，并查看工作区的节省与 ROI 指标。
Web executable，通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。
把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体，或 SourceWeft 对话中。智能体会读取该服务器的安装指南，先向你展示发布者、端点和登录方式，经你同意后再把它添加到你的客户端。密钥不会写进任何命令。
阅读 https://sourceweft.com/mcp/io.github.tokenzero-ai%2Ftokenzero/install.md，并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前，先告诉我它的发布者、端点和登录方式，等我确认。不要把 API 密钥写进命令或我会提交的文件；问我密钥应从哪里获取。把它添加到你客户端的 mcpServers 配置中。
{
"mcpServers": {
"tokenzero": {
"type": "http",
"url": "https://tokenzero.sh/mcp"
}
}
}Open-source tools from TokenZero, the bring-your-own-key gateway that cuts OpenAI, Anthropic and Gemini bills.
@tokenzero/mcp is a stdio MCP server for Claude Code, Cursor, Windsurf and Cline: audit the open project for token waste (locally), price model alternatives, make request bodies cache-friendly.@tokenzero/cli connects a project to the gateway with no code changes, audits LLM token waste locally, shows usage and verifies signed savings receipts.src/audit-core.ts) is the static token-waste audit used by the CLI, the hosted repo audit and the PR cost-diff check. It runs entirely on your machine.src/pricing.ts) lists the list prices every estimate is computed from, versioned and dated.Audits are static heuristics: they read code, not traffic. Numbers are estimates at list prices; verified savings come from the gateway's signed ledger once requests flow through it.
What it looks for:
cache_control, OpenAI prefix stability)Library and SDK repositories are detected and their findings downgraded, since their call sites pass through whatever the caller chooses.
One comment per PR, updated on every push; nothing leaves the runner. See action/README.md for inputs and outputs.
audit_repo_token_waste and calculate_model_arbitrage run entirely on your machine. optimize_prompt_payload sends the request body you give it to the TokenZero service (https://tokenzero.sh unless TOKENZERO_URL is set), so do not put secrets in it.
init audits locally, creates a workspace, and (with your consent) adds OPENAI_BASE_URL / ANTHROPIC_BASE_URL to .env. Your provider keys pass through untouched and are never stored.
Authentication: send the workspace key as the X-TokenZero-Key header (recommended). For zero-code setups the CLI can also embed it in the base URL (/w/<key>/v1); treat such URLs as secrets and use tokenzero rotate-key if one leaks.
License: Apache-2.0 · [email protected]
来源：README.md，提交 52982eb
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.
repofilesRewrite 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.
body必填endpointstrategyPrice 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.
model必填compare_toinput_tokens必填output_tokens必填static_tokensrequests_per_monthCreate 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.
nameLive 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.
keydemowindow已满足适用检查项的 100%
该评分衡量此收录条目的完整程度，依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价，也不表示服务器安全或当前可用：可连通性是带日期的检查结果，评分也不包含安装量或用户评价。
npx -y @tokenzero/cli audit # local, nothing is uploadednpx -y @tokenzero/cli audit --jsonnpx -y @tokenzero/cli audit --fail-over 30 # CI gate: exit 1 above 30% recoverablegit diff origin/main | npx -y @tokenzero/cli audit --diff - --format markdown# .github/workflows/tokenzero.ymlname: TokenZero cost checkon: pull_requestpermissions: { contents: read, pull-requests: write }jobs: cost-check: runs-on: ubuntu-latest steps: - uses: actions/checkout@v4 with: { fetch-depth: 0 } - uses: tokenzero-ai/tokenzero/action@v0claude mcp add tokenzero -- npx -y @tokenzero/mcp # Claude Code{ "mcpServers": { "tokenzero": { "command": "npx", "args": ["-y", "@tokenzero/mcp"] } } }npx -y @tokenzero/cli initnpm installnpm run build # bundles cli/bin/tokenzero.mjs (single file, no runtime deps)npm test