TokenZero

Claim this listing

io.github.tokenzero-ai/tokenzero

tokenzero-aiVerified

LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.

AI models & agents

Developer Tools Is TokenZero down?Alternatives

13 of 22 checks passed

Handshake
Tools listed
Updated recently

Responded

The server completed its last measured handshake. This is an observation, not a guarantee.

Connect to server

Median latency

1138 ms

Uptime, 30 days

Not measured

Last checked

23 hr ago

Measurement details

Core

Pass
Reachable
Latest probe returned HTTP 200 in 1138 ms.
23 hr ago
Pass
Valid handshake
protocolVersion 2025-11-25, serverInfo.name tokenzero.
23 hr ago
Pass
Lists tools
tools/list returned 6 tools.
23 hr ago
Pass
Current protocol
Negotiated 2025-11-25. The bar is 2025-06-18 or newer.
23 hr ago
Pass
HTTPS
The endpoint URL is https.

Performance

Not measured
Fast (p50)
Median latency 1138 ms over 1 samples in 7 days. The bar is 1000 ms. Need at least 5 samples.
Not measured
Consistent (p95)
95th percentile 1138 ms over 1 samples in 7 days. The bar is 3000 ms. Need at least 20 samples.
Not measured
Reliable (uptime)
1 of 1 attempts returned a tool list in 30 days (100%). The bar is 99%. Need at least 30 samples.
Not measured
Stable tool list
Fewer than two successful probes in 30 days, so tool-list stability is not measured.
23 hr ago

Access

Pass
Open access
tools/list succeeded with no credential, and the record declares none.
23 hr ago
Not measured
Standard auth
Auth is not required, so the OAuth metadata check does not apply.
Not measured
Free tier cited
No publisher quote has been checked.

Tools

Pass
Tools described
Every tool description is at least 20 characters.
23 hr ago
Pass
Valid input schemas
Every inputSchema is a JSON Schema object.
23 hr ago
Fail
Parameters documented
13 of 18 parameters have a description (72%). The bar is 80%.
23 hr ago
Pass
Safety hints
Every tool sets readOnlyHint or destructiveHint.
23 hr ago

Publisher

Pass
Verified namespace
Listed in the Official MCP Registry.
Not measured
Website matches publisher
This namespace is not a reverse domain, so the website comparison does not apply.
Pass
Source repo linked
A repository URL is on file.
Pass
Repo owner matches
The GitHub repository owner matches the namespace login.
Pass
Recently updated
Updated 2026-10-26T06:12:53.246204Z, within 180 days.
16 days ago
Not measured
Open-source licence
The GitHub licence lookup has not returned an OSI result yet.

Tools

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.
Measured 23 hr ago
calculate_model_arbitrage
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.
Measured 23 hr ago
optimize_prompt_payload
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.
Measured 23 hr ago
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.
Measured 23 hr ago
try_tokenzero
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": "..."}.
Measured 23 hr ago
workspace_metrics
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.
Measured 23 hr ago

Probe history

23 hr agook1138 ms6 tools

Status and uptime

Add badge to your README

The image links back to this page. It shows checks passed, or uptime, and the colour follows the latest status. Responses are cached for 5 to 15 minutes.

Markdown

[![MCP Heartbeat](https://mcpheartbeat.com/badge/io.github.tokenzero-ai/tokenzero.svg)](https://mcpheartbeat.com/s/io.github.tokenzero-ai/tokenzero)

HTML

<a href="https://mcpheartbeat.com/s/io.github.tokenzero-ai/tokenzero"><img alt="MCP Heartbeat" src="https://mcpheartbeat.com/badge/io.github.tokenzero-ai/tokenzero.svg"></a>

Uptime markdown

[![MCP Heartbeat uptime](https://mcpheartbeat.com/badge/io.github.tokenzero-ai/tokenzero.svg?kind=uptime)](https://mcpheartbeat.com/s/io.github.tokenzero-ai/tokenzero)

Served from https://mcpheartbeat.com.

Related servers

All alternatives

Same function and industry, ranked by checks passed then median latency.

Responded16 / 22 checks passed
Atako
atako.aiVerified
Remote MCP server to run your Atako AI agents: chat, projects, files, integrations and channels.
Developer Tools Code & DevOps
- AI models & agents
- Communication & social
- Handshake
- Tools listed
- Updated recently
Median latency 132 ms · Last checked 16 hr ago
Responded16 / 22 checks passed
A2UI Atomic Catalog
a2uicatalog.aiVerified
500+ typed UI atoms an agent composes into real rendered interfaces. Free, no API key.
Developer Tools Code & DevOps
- AI models & agents
- Handshake
- Tools listed
- Updated recently
Median latency 166 ms · Last checked 13 hr ago
Responded16 / 22 checks passed
CloudBrowser
cloudbrowser.aiVerified
Give AI agents a real cloud Chrome: open sessions, navigate, read pages, click, type and screenshot.
Developer Tools Code & DevOps
- AI models & agents
- Handshake
- Tools listed
- Updated recently
Median latency 198 ms · Last checked 16 hr ago
Responded16 / 22 checks passed
Drillr — The financial MCP for AI agents
drillr.aiVerified
Financial data and research MCP for US/CN/JP equities: filings, statements, ownership, signals.
Developer Tools Code & DevOps
- AI models & agents
- Knowledge & research
- Handshake
- Tools listed
- Updated recently
Median latency 566 ms · Last checked 16 hr ago
Responded15 / 22 checks passed
Sync My Cycle
GoodTurnStudioVerified
Your likely menstrual cycle phase today and this week, with food and workout ideas.
Developer Tools Code & DevOps
- Handshake
- Tools listed
- Updated recently
Median latency 34 ms · Last checked 14 hr ago
Responded15 / 22 checks passed
Feldspar free repository security scan
project-feldspar.comVerified
Free deterministic security scan of public git repos: OSV.dev vulnerable deps, secrets, config lint.
Developer Tools Code & DevOps
- Security & identity
- Developer tools & code
- Handshake
- Tools listed
- Updated recently
Median latency 35 ms · Last checked 15 hr ago

Connect to this server

Claude Code

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

Cursor .cursor/mcp.json

{
  "mcpServers": {
    "tokenzero": {
      "url": "https://tokenzero.sh/mcp"
    }
  }
}

VS Code .vscode/mcp.json

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