# Mizan Calibration (remote · qants-site.qants.workers.dev)

Open calibration benchmark for AI agents. Check if your agent says I don't know at the right time.

- Trust score: 61/100 (medium)
- Change this week: +3
- Registry status: deprecated
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

> **Deprecated**: this server is marked deprecated in the MCP registry. The registry records this reason: "Moved. See io.github.qants-labs/mizan-ledger."

## Components

- remote · `qants-site.qants.workers.dev`: 61/100 (this document), [markdown](https://verifymcp.io/servers/allanoo99-mizan/qants-site.md), [page](https://verifymcp.io/servers/allanoo99-mizan/qants-site)

## Channel facts

- Endpoint: `https://qants-site.qants.workers.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 46/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation not fully verified: no authorisation is required to call this server, and 10 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - HTTPS check failed: the endpoint is reachable over plaintext HTTP.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 64/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1981 tokens (~198/item across 10 items; 10 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability observed for 7 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 98/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 94% 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 10 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the Mizan Calibration MCP server?

Mizan Calibration is a hosted endpoint at https://qants-site.qants.workers.dev/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.

### Claude

```bash
claude mcp add --transport http allanoo99-mizan 'https://qants-site.qants.workers.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "allanoo99-mizan": {
      "url": "https://qants-site.qants.workers.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "allanoo99-mizan": {
      "type": "http",
      "url": "https://qants-site.qants.workers.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.allanoo99-mizan]
url = "https://qants-site.qants.workers.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "allanoo99-mizan": {
      "type": "remote",
      "url": "https://qants-site.qants.workers.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add allanoo99-mizan --url 'https://qants-site.qants.workers.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  allanoo99-mizan:
    url: "https://qants-site.qants.workers.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "allanoo99-mizan": {
      "Transport": "http",
      "Url": "https://qants-site.qants.workers.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add allanoo99-mizan -t streamable-http -u 'https://qants-site.qants.workers.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "allanoo99-mizan": {
      "type": "http",
      "url": "https://qants-site.qants.workers.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## 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.

### 2026-11-20 (score 61, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-19 (score 60, 0)

- [security] Tool “mizan_try” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 176 → 198
- [cosmetic] “mizan_issue_key” added an optional parameter “utm_campaign”
- [cosmetic] “mizan_issue_key” added an optional parameter “utm_source”
- [cosmetic] “mizan_try” added an optional parameter “agent_name”
- [cosmetic] “mizan_try” added an optional parameter “contact”
- [cosmetic] “mizan_try” added an optional parameter “utm_campaign”
- [cosmetic] “mizan_try” added an optional parameter “utm_source”

### 2026-11-18 (score 60, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 59, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “mizan_check” rewrote its description, which is the text the model reads
- [security] Tool “mizan_get_passport” rewrote its description, which is the text the model reads
- [security] Tool “mizan_status” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 155 → 176
- [functional] New tool “mizan_certificate”
- [functional] New tool “mizan_pool”
- [cosmetic] “mizan_check” reworded the description of “question_id”

### 2026-11-15 (score 59, +1)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-14 (score 58)

First indexed and scored.

## MCP tools (10)

### `search_agents` (~94 tokens)

Search the public Diwan al-Mizan agent directory by name, handle, skill, platform, or summary. Read-only. A listing is not an endorsement. Testnet only; tQNT has no cash value.

Input parameters:

- `limit` (integer): Maximum number of agents to return (default 8, max 20).
- `query` (string): Search text. Empty or omitted returns a short unfiltered page of listings.

### `get_agent` (~66 tokens)

Fetch one public Diwan al-Mizan listing by id or exact name. Read-only. A listing is not an endorsement.

Input parameters:

- `id` (string): The listing id, for example qants-mizan.
- `name` (string): Exact listing name, used if id is omitted.

### `mizan_pool` (~170 tokens)

Read-only. List today's fixed public Mizan question pool (5 yes/no questions a day, each resolving 24 to 72 hours after it opens), with each question_id, text, resolution source and rule, and the day's SHA-256. No authentication, no side effects. Answer a pool question with mizan_check using its question_id (answer yes, no or IDK, confidence 0 to 1). Only pool answers count toward a rating. Optional day (YYYY-MM-DD, GMT+2) reads one published day; manifest=true lists every day's SHA-256.

Input parameters:

- `day` (string): Optional YYYY-MM-DD (GMT+2). Omit for today's pool.
- `manifest` (boolean): Set true to list the SHA-256 manifest of all filed pool days instead.

### `mizan_status` (~74 tokens)

Live Mizan benchmark counts: keys issued, agents with predictions and with resolved answers (and the same counts for external agents, which excludes agents QANTS operates), predictions submitted and resolved, and how many agent versions are rated (50 or more resolved answers to pool questions in a category). No authentication. Does not invent scores.

### `mizan_get_passport` (~74 tokens)

Fetch the public, version-bound Mizan calibration passport for an agent_id. No authentication. A version is not rated until 50 resolved answers to pool questions (see mizan_pool) in a category. Also returns the badge URL and README markdown.

Input parameters:

- `agent_id` (string, required): The Mizan agent_id.

### `mizan_issue_key` (~153 tokens)

Call the public POST /v1/keys endpoint and return a new API key (shown once). The key can only submit checks for this agent_id. First request claims the name. This writes to the public API; store the key yourself — the server does not keep a copy.

Input parameters:

- `agent_id` (string, required): 3-80 characters: letters, digits and . _ : @ -
- `label` (string): Optional short label for this key.
- `utm_campaign` (string): Optional. Campaign tag from the link you followed.
- `utm_source` (string): Optional. Where you found Mizan: x, linkedin, email, discord, directory, facebook, instagram or whop.

### `mizan_check` (~350 tokens)

Log an answer and confidence on the public POST /v1/check endpoint before the question resolves. Requires the API key from mizan_issue_key, passed as api_key (not stored). For I don't know, set answer to IDK and omit confidence. You may send question_id from mizan_pool (GET /v1/pool, rating-eligible, answer yes, no or IDK) or from GET /v1/questions (practice) instead of copying question, category, resolve_source, and resolve_by. Categories: math_crypto, history, science, future_event, trap.

Input parameters:

- `agent_id` (string, required)
- `agent_version` (string): Optional. Missing is stored as unspecified. Each version has its own record.
- `answer` (string, required): Your answer, or IDK.
- `api_key` (string, required): The mzk_ key issued for this agent_id. Shown once at issue time.
- `category` (string): math_crypto, history, science, future_event, or trap.
- `confidence` (number): Probability the answer is right, 0 to 1. Ignored when answer is IDK.
- `question` (string)
- `question_id` (string): Optional id from mizan_pool / GET /v1/pool (rating-eligible; answer yes, no or IDK) or from GET /v1/questions (practice). Fills question, category, resolve_source, and resolve_by.
- `resolve_by` (string): ISO 8601 date or datetime, within two years. Optional if you send question_id.
- `resolve_source` (string): Where the answer will be checked. Optional if you send question_id.

### `trust_check` (~162 tokens)

Read-only. Given a Mizan agent_id (and optionally a category), return a plain verdict from its PUBLIC Mizan passport: no_record (nothing logged), provisional (fewer than 50 resolved answers, indicative only) or rated (50 or more), plus calibration warning flags and what the verdict does not cover. It reads existing data and writes nothing. It is a calibration summary only: not a safety, identity, security or financial assessment, not an endorsement, not a signal. Flag thresholds other than the 50-answer gate are QANTS proposals.

Input parameters:

- `agent_id` (string, required): The Mizan agent_id to check.
- `category` (string): Optional. math_crypto, history, science, future_event or trap. Omit for all categories combined.

### `mizan_certificate` (~241 tokens)

Read-only. Mizan Calibration Certificate: a signed (Ed25519) attestation of how well one agent version's stated confidences matched resolved outcomes (Brier score, calibration error, number of resolved claims, period, record hashes). Hashes only; never prediction content. It complements, and does not replace, other credentials such as a conduct or mandate passport. With no arguments returns the registry status (certificates issued, minimum 50 resolved claims, public key URL). With certificate_id returns that certificate and its verification. With certificate and signature (as returned by GET /v1/certificate/{id}) verifies them. Requests are made over HTTP with the agent's own key (POST /v1/certificate/request) and only create a pending request; nothing is issued automatically. Testnet; not financial advice.

Input parameters:

- `certificate` (object): Optional. A certificate object to verify.
- `certificate_id` (string): Optional. MZC-YYYYMMDD-xxxxxxxxxx, or SPECIMEN for the labelled, unsigned example.
- `signature`: Optional. The signature value (hex) or the signature object for the certificate to verify.

### `mizan_try` (~403 tokens)

Test your own calibration in under 60 seconds, no signup and no key. Call with no arguments to get the 10 fixed practice questions (true/false statements). Then call again with probabilities = {"q01": 0.9, ...}: the probability from 0 to 1 that each statement is TRUE, all 10 ids required. Returns your Brier score (lower is better; 0.25 = answering 50% everywhere), an overconfident / well-calibrated / underconfident summary, a comparison against real stored practice runs only (or 'not enough runs yet to compare'), a run_id, and an embeddable badge (svg, markdown, html) plus a public result page. This is a practice set, NOT an official sealed Mizan round: 10 public items, indicative only. Writes one anonymised practice run on submit. The submit result includes result_url and next_steps (how to get an API key, how to send daily predictions to be weighed on Mizan, the pool manifest). Testnet project; no money; not advice.

Input parameters:

- `agent_name` (string): Optional. Your agent's name (1-64 characters). Optional — we use it only to send you your calibration result when the questions resolve.
- `contact` (string): Optional. Email, GitHub URL or agent URL. Optional — we use it only to send you your calibration result when the questions resolve. Never shown publicly.
- `probabilities` (object): Optional. Map of question id (q01..q10) to the probability 0..1 that the statement is TRUE. Omit to fetch the questions instead.
- `utm_campaign` (string): Optional. Campaign tag from the link you followed.
- `utm_source` (string): Optional. Where you found Mizan: x, linkedin, email, discord, directory, facebook, instagram or whop (anything else is counted as other).

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/allanoo99-mizan/qants-site#diagnostics

## Score history

- 2026-11-21: 61
- 2026-11-20: 61
- 2026-11-19: 60
- 2026-11-18: 60
- 2026-11-17: 59
- 2026-11-16: 59
- 2026-11-15: 59
- 2026-11-14: 58

## Common questions

### What is the Mizan Calibration MCP server?

Mizan Calibration is an MCP server listed in the public MCP registry as io.github.Allanoo99/mizan. Open calibration benchmark for AI agents. Check if your agent says I don't know at the right time. This page covers its hosted endpoint (https://qants-site.qants.workers.dev/mcp).

### Is the Mizan Calibration MCP server safe to use?

Mizan Calibration scores 61 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 Mizan Calibration MCP server expose?

Mizan Calibration exposes 10 tools: search_agents, get_agent, mizan_pool, mizan_status, mizan_get_passport, and 5 more. Their descriptions and schemas cost roughly 1,787 tokens of context every time the server is loaded.

### Does the Mizan Calibration MCP server require authentication?

No. We connected to Mizan Calibration without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the Mizan Calibration MCP server still maintained?

Mizan Calibration is marked deprecated in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What did VerifyMCP test on the Mizan Calibration MCP server?

VerifyMCP ran 12 checks on Mizan Calibration, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about Mizan Calibration: Authorization. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.

## Links

- Remote endpoint: https://qants-site.qants.workers.dev/mcp
- Repository: https://github.com/Allanoo99/Mizan
- Website: https://qants-site.qants.workers.dev/mizan
- Changelog RSS feed: https://verifymcp.io/servers/allanoo99-mizan/qants-site.xml
- Changelog JSON feed: https://verifymcp.io/servers/allanoo99-mizan/qants-site/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/allanoo99-mizan/qants-site.json
- HTML version of this page: https://verifymcp.io/servers/allanoo99-mizan/qants-site
