Connect

8 clients · secrets stay placeholders

JSON (mcpServers)Claude CodeCodexOpenCodeCursorVS CodeGemini CLIGoose

{
  "mcpServers": {
    "tokenzero": {
      "type": "http",
      "url": "https://api.tokenzero.sh/mcp"
    }
  }
}

claude mcp add --transport http tokenzero https://api.tokenzero.sh/mcp

[mcp_servers.tokenzero]
url = "https://api.tokenzero.sh/mcp"

{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "tokenzero": {
      "type": "remote",
      "url": "https://api.tokenzero.sh/mcp",
      "enabled": true
    }
  }
}

{
  "mcpServers": {
    "tokenzero": {
      "type": "http",
      "url": "https://api.tokenzero.sh/mcp"
    }
  },
  "deeplink": "cursor://anysphere.cursor-deeplink/mcp/install?name=tokenzero&config=eyJ0eXBlIjoiaHR0cCIsInVybCI6Imh0dHBzOi8vYXBpLnRva2VuemVyby5zaC9tY3AifQ%3D%3D"
}

{
  "servers": {
    "tokenzero": {
      "type": "http",
      "url": "https://api.tokenzero.sh/mcp"
    }
  }
}

{
  "mcpServers": {
    "tokenzero": {
      "httpUrl": "https://api.tokenzero.sh/mcp"
    }
  }
}

extensions:
  "tokenzero":
    enabled: true
    name: "tokenzero"
    type: streamable_http
    uri: "https://api.tokenzero.sh/mcp"
    timeout: 300

Quality 95 / 100strong

protocol100 · weight 25

pass
protocol.modernsupports 2026-07-28 (server/discover)
pass
protocol.statelessanswers without a session
pass
protocol.transportstreamable HTTP
pass
protocol.list_ttltool list is cacheable (ttlMs 3600000)

authorizationn/a · weight 15

n/a
auth.prm, auth.as_metadata, auth.cimdno remote uses OAuth
n/a
auth.secret_in_urlno templated URL

tool hygiene100 · weight 30

pass
tools.descriptionsevery tool has a description
pass
tools.description_lengthdescriptions are concise
pass
tools.schemasevery tool has an object input schema
pass
tools.annotations6 of 6 tools declare readOnlyHint or destructiveHint
pass
tools.directory_hintsevery tool declares readOnlyHint, destructiveHint, idempotentHint and openWorldHint
pass
tools.token_costabout 1,192 tokens to load every tool
pass
tools.api_dumptools are not a one-to-one API dump

stability75 · weight 15

warn
stability.changes11 tool changes in 30 days
pass
stability.rug_pullno tool changed its meaning under the same name

dependenciesn/a · weight 15

n/a
deps.known_vulns, deps.mcp_sdk_version, deps.resolvabledeps.dev does not know @tokenzero/[email protected]

6 tools, about 1,192 tokens to load them all · tool set 696968a33694 · tools last changed 2026-11-01 · checked 2026-11-07 18:01 UTC

Tool changes

2026-11-01calculate_model_arbitragechangeddescription
before
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: cost per request and per month for the requested model, its cheaper sibling, and the effect of prompt caching. Pricing table version 2026-10-28.
after · 87% of words in common
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: cost per request and per month for the requested model, its cheaper sibling, and the effect of prompt caching. The result names the pricing table version it used.
2026-11-01try_tokenzeroadded
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 formatting, edge cache, cascade advice, signed receipt) on a sample or your own prompt and model, and returns the list-price saving, the signed receipt and a copy-paste keyless curl that makes a real call on a free model. Pass {} for the default, or {"model": "gpt-6.1-sol", "system": "...", "prompt": "..."}.
2026-10-29calculate_model_arbitragechangeddescription, input schema
before
Price 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.
after · 57% of words in common
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: cost per request and per month for the requested model, its cheaper sibling, and the effect of prompt caching. Pricing table version 2026-10-28.
2026-10-29optimize_prompt_payloadchangeddescription
before
Rewrite 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.
after · 93% of words in common
No API key needed. Rewrite 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.
2026-10-29audit_repo_token_wastechangeddescription
before
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.
after · 54% of words in common
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, frontier models on extraction tasks, hot loops, non-deterministic repeat calls, and prompt-caching mis-integration (caching gated on model names, volatile values in the system prompt, random ids in history, wrong-provider cache markers, misplaced breakpoints, cost math that ignores cached tokens). Returns findings with fixes and an estimated recoverable percentage.
2026-10-28calculate_model_arbitragechangeddescription
before
Price 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.
after · 94% of words in common
Price 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.
2026-10-27workspace_metricschangedtitle, annotations
2026-10-27provision_workspacechangedtitle, annotations
2026-10-27calculate_model_arbitragechangedtitle, annotations
2026-10-27optimize_prompt_payloadchangedtitle, annotations

Showing the latest 10. Full history: list_changes · trend: quality JSON.

Checks run on what our credential-free, read-only probes observe; tools are never called and no code audit is performed. How it is computed.

Trust 95 / 100

provenance85

liveness97

freshness100

hygiene100

+repository +dns-namespace +website +reachable +uptime-91% +updated-2d-ago

Derived from observable signals (official registry feed and our own credential-free probes); no code audit performed. How it is computed.

Dependencies

@tokenzero/[email protected] npmthis version is not known to the dependency resolver

Dependency graphs from deps.dev; advisories from OSV.dev, including the GitHub Advisory Database and the PyPI Advisory Database; all CC BY 4.0. The graph is what a clean install of this version resolves today; nothing was installed or run. How it is checked.

Endpoints

remote	auth	reachable	uptime 30d	p50	protocol	last ok
`https://api.tokenzero.sh/mcp` streamable-http	none	yes	91%	534 ms	2026-07-28	2026-11-07

package	registry	version	runtime	secrets
`@tokenzero/mcp`	npm	0.3.0	–	`TOKENZERO_KEY`

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, frontier models on extraction tasks, hot loops, non-deterministic repeat calls, and prompt-caching mis-integration (caching gated on model names, volatile values in the system prompt, random ids in history, wrong-provider cache markers, misplaced breakpoints, cost math that ignores cached tokens). Returns findings with fixes and an estimated recoverable percentage.
`calculate_model_arbitrage`read-only	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: cost per request and per month for the requested model, its cheaper sibling, and the effect of prompt caching. The result names the pricing table version it used.
`optimize_prompt_payload`read-only	No API key needed. Rewrite 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.
`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-click dashboard link and the badge URL. Free up to the monthly free tier; nothing is billed.
`try_tokenzero`read-only	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 formatting, edge cache, cascade advice, signed receipt) on a sample or your own prompt and model, and returns the list-price saving, the signed receipt and a copy-paste keyless curl that makes a real call on a free model. Pass {} for the default, or {"model": "gpt-6.1-sol", "system": "...", "prompt": "..."}.
`workspace_metrics`read-only	Live 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.

Schemas: list_tools.

Also listed as

1 other active names share this repository: io.github.tokenzero-ai/tokenzero

Similar MCP servers

Official server.json

{
  "name": "sh.tokenzero/mcp",
  "title": "TokenZero",
  "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
  "remotes": [
    {
      "url": "https://api.tokenzero.sh/mcp",
      "type": "streamable-http"
    }
  ],
  "version": "0.3.0",
  "packages": [
    {
      "version": "0.3.0",
      "transport": {
        "type": "stdio"
      },
      "identifier": "@tokenzero/mcp",
      "registryType": "npm",
      "environmentVariables": [
        {
          "name": "TOKENZERO_URL",
          "description": "Gateway base URL (default https://tokenzero.sh)"
        },
        {
          "name": "TOKENZERO_KEY",
          "isSecret": true,
          "description": "Workspace key (tz_live_…) for workspace_metrics; optional"
        }
      ]
    }
  ],
  "repository": {
    "url": "https://github.com/tokenzero-ai/tokenzero",
    "source": "github"
  },
  "websiteUrl": "https://tokenzero.sh",
  "description": "Ledger of record for AI spend: verifiable receipts, waste auditor & model arbitrage MCP."
}