TokenZero
REMOTE · TOKENZERO.SH
LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server.
Available components
Last scanned (20 hours ago)
Scores higher than 69% of remote servers
Reachable. Last reached 4 Nov 2026.
Category AI and Machine Learning
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability76
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 974 tokens (~162/item across 6 items; 6 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management30
- Stability observed for 9 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage91
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 72% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 6 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 7 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 0
- Server version: 0.2.15 → 0.2.16 functional
- 3 Nov 26 +1
- Server version: 0.2.12 → 0.2.15 functional
- 2 Nov 26 0
- Server version: 0.2.11 → 0.2.12 functional
- 1 Nov 26 +3
- The server rewrote its instructions, which are the text every model session reads security
- Tool “calculate_model_arbitrage” rewrote its description, which is the text the model reads security
- Schema quality: 781 → 974 ▼ functional
- Tool coverage: 67% → 72% ▲ functional
- The server now declares the “prompts” capability functional
- First check of Schema quality: 100 functional
- New prompt “cut-my-llm-bill” functional
- New prompt “price-my-workload” functional
- New prompt “try-tokenzero” functional
- Server version: 0.2.9 → 0.2.11 functional
- New tool “try_tokenzero” functional
- 31 Oct 26 +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.
- 29 Oct 26 0
- Tool “audit_repo_token_waste” rewrote its description, which is the text the model reads security
- Tool “calculate_model_arbitrage” rewrote its description, which is the text the model reads security
- Tool “optimize_prompt_payload” rewrote its description, which is the text the model reads security
- Schema quality: 129 → 156 ▼ functional
- Tool coverage: 47% → 67% ▲ functional
- Server version: 0.2.8 → 0.2.9 functional
- “calculate_model_arbitrage” reworded the description of “input_tokens” cosmetic
- “calculate_model_arbitrage” reworded the description of “model” cosmetic
- “calculate_model_arbitrage” reworded the description of “output_tokens” cosmetic
- “calculate_model_arbitrage” made “input_tokens” optional cosmetic
- “calculate_model_arbitrage” made “output_tokens” optional cosmetic
- 28 Oct 26 +1
- Tool “calculate_model_arbitrage” rewrote its description, which is the text the model reads security
- Server version: 0.2.7 → 0.2.8 functional
- 27 Oct 26 +7
- Authorization: unverified → partial ▲ security
- The server rewrote its instructions, which are the text every model session reads security
- Schema quality: pass → fail ▼ functional
- Stability: unverified → 0.03 ▲ functional
- Server version: 0.2.2 → 0.2.7 functional
- Tool “audit_repo_token_waste” changed its title: Audit a repo for LLM token waste cosmetic
- Tool “calculate_model_arbitrage” changed its title: Price a workload across models cosmetic
- Tool “optimize_prompt_payload” changed its title: Make a request body cache-friendly cosmetic
- Tool “provision_workspace” changed its title: Create a free TokenZero workspace cosmetic
- Tool “workspace_metrics” changed its title: Read a workspace savings scorecard cosmetic
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 4 Nov 2026 · Probed https://tokenzero.sh/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=tokenzero.sh | CN=YE1,O=Let's Encrypt,C=US | 25 Oct 2026 | 23 Jan 2027 | ECDSA 256 | ECDSA-SHA384 | 508175c1f63c4febe2cca36f79e379061df |
| SANs: *.tokenzero.sh, tokenzero.sh | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of tokenzero.sh. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| sh. | present | 34349 | 8 | Verified |
| tokenzero.sh. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000; includeSubDomains; preload |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | no-referrer |
| permissions-policy | camera=(), microphone=(), geolocation=(), payment=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://tokenzero.sh/mcp | Verified | 200 | |
| http (plaintext) | http://tokenzero.sh/mcp | HTTPS enforced | 301 | https://tokenzero.sh/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
audit_repo_token_waste Audit a repo for LLM token waste ~149
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.
| Name | Type | Req | Description |
|---|---|---|---|
| files | array | – | Alternative to repo: files to analyze |
| repo | string | – | GitHub owner/name (public) |
No output schema declared.
No examples provided.
calculate_model_arbitrage Price a workload across models ~187
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.
| Name | Type | Req | Description |
|---|---|---|---|
| compare_to | array | – | – |
| input_tokens | number | – | per request; default 2000 |
| model | string | yes | 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) |
No output schema declared.
No examples provided.
optimize_prompt_payload Make a request body cache-friendly ~99
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.
| Name | Type | Req | Description |
|---|---|---|---|
| body | object | yes | The request body |
| endpoint | string | – | – |
| strategy | string | – | – |
No output schema declared.
No examples provided.
provision_workspace Create a free TokenZero workspace ~80
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.
| Name | Type | Req | Description |
|---|---|---|---|
| name | string | – | workspace name (default mcp-agent) |
No output schema declared.
No examples provided.
try_tokenzero Try TokenZero (no key needed) ~169
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": "..."}.
| Name | Type | Req | Description |
|---|---|---|---|
| model | string | – | a priced model id; default gpt-6.1-sol |
| prompt | string | – | your user message (optional) |
| system | string | – | your system prompt (optional) |
No output schema declared.
No examples provided.
workspace_metrics Read a workspace savings scorecard ~102
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.
| Name | Type | Req | Description |
|---|---|---|---|
| demo | boolean | – | return the sample scorecard instead |
| key | string | – | workspace key (tz_live_…) |
| window | string | – | – |
No output schema declared.
No examples provided.
How do I install the TokenZero MCP server?
TokenZero is a hosted endpoint at https://tokenzero.sh/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · tokenzero.sh
claude mcp add --transport http tokenzero-ai-tokenzero 'https://tokenzero.sh/mcp'
What is the TokenZero MCP server?
TokenZero is an MCP server listed in the public MCP registry as io.github.tokenzero-ai/tokenzero. LLM cost optimization gateway, repo token-waste auditor & model arbitrage MCP server. This page covers its hosted endpoint (https://tokenzero.sh/mcp).
Is the TokenZero MCP server safe to use?
TokenZero scores 77 out of 100 on VerifyMCP. 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, optimize_prompt_payload, calculate_model_arbitrage, provision_workspace, workspace_metrics. Their descriptions and schemas cost roughly 786 tokens of context every time the server is loaded.
Does the TokenZero MCP server require authentication?
No. We connected to TokenZero without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
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.