io.github.tokenzero-aiPublished by GitHub account tokenzero-aiv0.2.2Updated Oct 26, 2026
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
The publisher's own server: TokenZero
TokenZero audits code for LLM token waste, rewrites request bodies for prompt caching, prices model alternatives and reports workspace savings.
Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.
Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.
Read https://sourceweft.com/mcp/io.github.tokenzero-ai%2Ftokenzero/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.Add this to your client's mcpServers config.
{
"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]
Source: README.md at commit 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.
bodyrequiredendpointstrategyPrice 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.
modelrequiredcompare_toinput_tokensrequiredoutput_tokensrequiredstatic_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.
keydemowindow100% of the applicable checks met
How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.
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