# TokenZero (npm · @tokenzero/mcp)

Ledger of record for AI spend: verifiable receipts, waste auditor & model arbitrage MCP.

- Trust score: 74/100 (medium)
- Change this week: +6
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-04

## Components

- remote · `api.tokenzero.sh`: 77/100, [markdown](https://verifymcp.io/servers/sh-tokenzero-mcp/api.md), [page](https://verifymcp.io/servers/sh-tokenzero-mcp/api)
- npm · `@tokenzero/mcp`: 74/100 (this document), [markdown](https://verifymcp.io/servers/sh-tokenzero-mcp/tokenzero-mcp.md), [page](https://verifymcp.io/servers/sh-tokenzero-mcp/tokenzero-mcp)

## Channel facts

- Registry: `npm`
- Package: `@tokenzero/mcp`
- Version: `0.3.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-04.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (Apache-2.0).
  - Actively maintained (last published 0 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 76/100
  - 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 890 tokens (~148/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 30/100
  - Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 88/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 63% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the TokenZero MCP server?

TokenZero runs locally as an npm package, launched with npx -y @tokenzero/mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add sh-tokenzero-mcp -- npx -y @tokenzero/mcp
```

### Cursor

```json
{
  "mcpServers": {
    "sh-tokenzero-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@tokenzero/mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "sh-tokenzero-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@tokenzero/mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add sh-tokenzero-mcp -- npx -y @tokenzero/mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "sh-tokenzero-mcp": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@tokenzero/mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add sh-tokenzero-mcp --command npx --arg -y --arg @tokenzero/mcp
```

### Hermes

```yaml
mcp_servers:
  sh-tokenzero-mcp:
    command: "npx"
    args: ["-y", "@tokenzero/mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "sh-tokenzero-mcp": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "@tokenzero/mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add sh-tokenzero-mcp -t stdio -c npx -a -y @tokenzero/mcp
```

### Other

```json
{
  "mcpServers": {
    "sh-tokenzero-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@tokenzero/mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-04 (score 74, +15)

- [security improvement] Malware scan: unverified → pass

### 2026-11-03 (score 59, +12)

- [security improvement] Known CVEs: unverified → pass
- [security improvement] Malware scan: unverified → pass
- [functional regression] Security disclosure: fail → unverified
- [functional improvement] Dependency health: unverified → pass
- [functional] Package version: 0.2.14 → 0.2.16
- [functional] Package version: 0.2.14 → 0.2.15

### 2026-11-02 (score 47, −26)

- [security regression] Known CVEs: pass → unverified
- [security regression] Malware scan: pass → unverified
- [functional regression] Dependency health: pass → unverified
- [functional] Package version: 0.2.12 → 0.2.14
- [functional] Package version: 0.2.12 → 0.2.13

### 2026-11-01 (score 73, +3)

- [security regression] Stability: 0.17 → unverified
- [security regression] Tool safety: pass → unverified
- [security regression] Known CVEs: pass → unverified
- [functional regression] Schema quality: 705 → 890
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Dependency health: pass → unverified
- [functional improvement] Tool coverage: 56% → 63%
- [functional] First check of Schema quality: unverified
- [functional] First check of Schema quality: 100
- [functional] Package version: 0.2.9 → 0.2.12
- [functional] Package version: 0.2.9 → 0.2.11

### 2026-10-31 (score 70, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-29 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-10-28 (score 68, +15)

- [security regression] Tool safety: pass → unverified
- [security regression] Stability: 0.03 → unverified
- [security improvement] Malware scan: unverified → pass
- [functional regression] Tool coverage: 100 → unverified
- [functional regression] Capabilities: pass → unverified
- [functional regression] Schema quality: pass → fail
- [functional improvement] Tool coverage: 38% → 56%
- [functional] First check of Schema quality: unverified
- [functional] Package version: 0.2.8 → 0.2.9

### 2026-10-27 (score 53, +1)

- [security regression] Known CVEs: pass → unverified
- [functional regression] Dependency health: pass → unverified
- [functional improvement] Stability: unverified → 0.03
- [functional] Package version: 0.2.6 → 0.2.8
- [functional] Package version: 0.2.6 → 0.2.7

## MCP tools (6)

### `try_tokenzero` (~183 tokens)

Try TokenZero (no key needed)

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": "..."}. Runs in the TokenZero service; send no secrets in the prompt.

Input parameters:

- `model` (string): a priced model id; default gpt-6.1-sol
- `prompt` (string): your user message (optional)
- `system` (string): your system prompt (optional)

### `audit_repo_token_waste` (~192 tokens)

Audit a repo or directory for LLM token waste

No API key needed. Static audit for LLM token waste: uncached static prompts and prompt templates, frontier models on extraction/classification prompts, calls in loops, unpriced models, 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). Give `path` for a local directory (scanned on this machine, nothing uploaded; defaults to the working directory), `repo` (owner/name) for a public GitHub repo, or `diff` for a unified diff. Results are static heuristics, not measurements.

Input parameters:

- `diff` (string): unified diff text, e.g. from git diff
- `path` (string): local directory; defaults to the current working directory
- `repo` (string): public GitHub owner/name

### `calculate_model_arbitrage` (~159 tokens)

Price a workload across models

No API key needed; only `model` is required (defaults 2,000 tokens in and 400 out). Price a workload at list prices for the requested model, its cheaper sibling and any extra models, with and without prompt caching. Runs locally.

Input parameters:

- `compare_to` (array)
- `input_tokens` (number): per request; default 2000
- `model` (string, required): model id, e.g. gpt-6.1-sol or claude-sonnet-5-5
- `output_tokens` (number): per request; default 400
- `requests_per_month` (number)
- `static_tokens` (number): portion of input_tokens that is a fixed prefix (system + tools)

### `optimize_prompt_payload` (~80 tokens)

Make a request body cache-friendly

Rewrite an OpenAI Chat/Responses or Anthropic Messages request body so its static prefix is provider-cacheable, and project the saving. Sends the body you pass to the TokenZero service (set TOKENZERO_URL); do not pass secrets in it.

Input parameters:

- `body` (object, required)
- `endpoint` (string)
- `strategy` (string)

### `workspace_metrics` (~109 tokens)

Read a workspace savings scorecard

Live value scorecard for a TokenZero workspace (GET /v1/workspaces/me/metrics): hard savings and net ROI per window, per-engine contribution, speed, parity, availability, privacy posture, per-model breakdown and one-click recommendations. Uses TOKENZERO_KEY unless a key is given; demo: true returns a labelled sample.

Input parameters:

- `demo` (boolean)
- `key` (string): workspace key (tz_live_…); defaults to TOKENZERO_KEY
- `window` (string)

### `provision_workspace` (~95 tokens)

Create a free TokenZero workspace

Create a TokenZero workspace and key with no form (POST /v1/workspaces on the TokenZero service). Returns the key once, the base URLs that route through it, the one-click dashboard link (key in the URL fragment, never sent to the server) and the badge URL. Free up to the monthly free tier; nothing is billed.

Input parameters:

- `name` (string): workspace name (defaults to "mcp-agent")

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/sh-tokenzero-mcp/tokenzero-mcp#diagnostics

## Score history

- 2026-11-04: 74
- 2026-11-03: 59
- 2026-11-02: 47
- 2026-11-01: 73
- 2026-10-31: 70
- 2026-10-30: 69
- 2026-10-29: 69
- 2026-10-28: 68
- 2026-10-27: 53
- 2026-10-26: 52

## Common questions

### What is the TokenZero MCP server?

TokenZero is an MCP server listed in the public MCP registry as sh.tokenzero/mcp. Ledger of record for AI spend: verifiable receipts, waste auditor & model arbitrage MCP. This page covers its npm package (@tokenzero/mcp).

### Is the TokenZero MCP server safe to use?

TokenZero scores 74 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 4 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the TokenZero MCP server expose?

TokenZero exposes 6 tools: try_tokenzero, audit_repo_token_waste, calculate_model_arbitrage, optimize_prompt_payload, workspace_metrics, provision_workspace. Their descriptions and schemas cost roughly 818 tokens of context every time the server is loaded.

### Is the TokenZero MCP server still maintained?

TokenZero is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the TokenZero MCP server under?

TokenZero declares the Apache-2.0 licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- npm package: https://www.npmjs.com/package/@tokenzero/mcp
- Socket report: https://socket.dev/npm/package/@tokenzero/mcp
- Repository: https://github.com/tokenzero-ai/tokenzero
- Website: https://tokenzero.sh/
- Changelog RSS feed: https://verifymcp.io/servers/sh-tokenzero-mcp/tokenzero-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/sh-tokenzero-mcp/tokenzero-mcp.json
- HTML version of this page: https://verifymcp.io/servers/sh-tokenzero-mcp/tokenzero-mcp