Mizan calibration benchmark
● Activeio.github.qants-labs/mizan
Does your agent say 'I don't know' at the right time? Brier-scored calibration passports.
Connect this server
One click to install, or copy the config below. Suits: Cursor · HTTP clients.
Or add it manually — claude_desktop_config.json (Claude Desktop) or .cursor/mcp.json (Cursor):
{
"mcpServers": {
"mizan": {
"url": "https://qants-site.qants.workers.dev/mcp"
}
}
}claude mcp add --transport http mizan https://qants-site.qants.workers.dev/mcpcode --add-mcp '{"name":"mizan","type":"http","url":"https://qants-site.qants.workers.dev/mcp"}'Syntax from each client's docs (Claude Code: claude mcp add; Codex: codex mcp add; VS Code: code --add-mcp). Placeholders in angle brackets are values you fill in. Codex takes hosted servers in config.toml ([mcp_servers.<name>] url = …) rather than on the command line.
A starting point — check the repository for exact arguments and setup. Restart your client after editing the config.
- Category
- Legal & Government
- Version
- 1.1.0
- Registry
- active
- Published
- 11/20/2026
Is it safe? Is it maintained?
Serverdex check: Nov 22, 2026Looks healthy: Mizan calibration benchmark is maintained, open source, hosted endpoint answering without a key.
- Maintained
- Active
- Last commit 2 days ago (Nov 20, 2026), 0 open issues.
- Official registry
- Active
- Published as io.github.qants-labs/mizan in the official MCP registry, version 1.1.0.
- Source
- Open source, MIT
- Public repository under the MIT licence, 0 stars, 0 forks.
- Runs
- Hosted by the publisher
- Your client talks to qants-site.qants.workers.dev: prompts and tool arguments leave your machine for that host.
- Credentials
- None needed to connect
- The hosted endpoint completed the Serverdex initialize + tools/list handshake with no key (checked Nov 22, 2026); individual tools may still ask for one.
- Owner
- Unclaimed
- Nobody has claimed this page yet; the data above comes from the registry, GitHub and the live check.
Facts only: last commit and licence from GitHub, the entry's status from the official registry, credentials from the live check. Not a code audit — run the security scan on the endpoint yourself and see the status history.
Live check
checked Nov 22, 2026, 07:08 UTCStatus history & uptime →The endpoint answered the MCP handshake as "Mizan and Diwan al-Mizan" and listed 10 tools. Answering since Nov 21, 2026.
Context cost ≈ 2.3k tokens of tool definitions a client loads per conversation (estimate: characters ÷ 4) across 10 tools.
Tools (10)
search_agents2 paramsSearch 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.
Show parametersHide parameters
querystringSearch text. Empty or omitted returns a short unfiltered page of listings.limitintegerMaximum number of agents to return (default 8, max 20).
get_agent2 paramsFetch one public Diwan al-Mizan listing by id or exact name. Read-only. A listing is not an endorsement.
Show parametersHide parameters
idstringThe listing id, for example qants-mizan.namestringExact listing name, used if id is omitted.
mizan_pool2 paramsRead-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.
Show parametersHide parameters
daystringOptional YYYY-MM-DD (GMT+2). Omit for today's pool.manifestbooleanSet true to list the SHA-256 manifest of all filed pool days instead.
mizan_statusLive 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_passport1 paramFetch 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.
Show parametersHide parameters
agent_idstringrequiredThe Mizan agent_id.
mizan_issue_key4 paramsCall 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.
Show parametersHide parameters
agent_idstringrequired3-80 characters: letters, digits and . _ : @ -labelstringOptional short label for this key.utm_sourcestringOptional. Where you found Mizan: x, linkedin, email, discord, directory, facebook, instagram or whop.utm_campaignstringOptional. Campaign tag from the link you followed.
mizan_check10 paramsLog 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.
Show parametersHide parameters
api_keystringrequiredThe mzk_ key issued for this agent_id. Shown once at issue time.agent_idstringrequiredagent_versionstringOptional. Missing is stored as unspecified. Each version has its own record.questionstringcategorystringmath_crypto, history, science, future_event, or trap.answerstringrequiredYour answer, or IDK.confidencenumberProbability the answer is right, 0 to 1. Ignored when answer is IDK.resolve_sourcestringWhere the answer will be checked. Optional if you send question_id.resolve_bystringISO 8601 date or datetime, within two years. Optional if you send question_id.question_idstringOptional id from mizan_pool / GET /v1/pool (rating-eligible; answer yes, no or IDK) or from GET /v1/questions (practice). Fills question, category, resolve_sour
trust_check2 paramsRead-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.
Show parametersHide parameters
agent_idstringrequiredThe Mizan agent_id to check.categorystringOptional. math_crypto, history, science, future_event or trap. Omit for all categories combined.
mizan_certificate3 paramsRead-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.
Show parametersHide parameters
certificate_idstringOptional. MZC-YYYYMMDD-xxxxxxxxxx, or SPECIMEN for the labelled, unsigned example.certificateobjectOptional. A certificate object to verify.signatureOptional. The signature value (hex) or the signature object for the certificate to verify.
mizan_try5 paramsTest 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.
Show parametersHide parameters
probabilitiesobjectOptional. Map of question id (q01..q10) to the probability 0..1 that the statement is TRUE. Omit to fetch the questions instead.agent_namestringOptional. Your agent's name (1-64 characters). Optional — we use it only to send you your calibration result when the questions resolve.contactstringOptional. Email, GitHub URL or agent URL. Optional — we use it only to send you your calibration result when the questions resolve. Never shown publicly.utm_sourcestringOptional. Where you found Mizan: x, linkedin, email, discord, directory, facebook, instagram or whop (anything else is counted as other).utm_campaignstringOptional. Campaign tag from the link you followed.
Checked by Serverdex with a plain initialize + tools/list call to qants-site.qants.workers.dev/mcp, no credentials, about once a day. A failed check is never a removal.
On GitHub
read Nov 21, 2026- Stars
- 0
- Forks
- 0
- Last push
- Nov 20, 2026
- License
- MIT
Python
From the README
mizan-ledger Declare how confident your agent is before a task, commit a salted hash of that declaration, then score honesty against the real outcome (your own tests, evals or checks). Local-first, hash-only, verifiable offline. Status: v0.1.5, early alpha by QANTS. On PyPI (not on npm). MIT licensed (see LICENSE). No network access, no telemetry, no dependencies in the core library. Why Agents often report success with the same unearned confidence whether they are right or wrong. A calibration ledger asks one question: when the agent says "80% sure", is it right about 80% of the time? Brier score and ECE answer that. The commitment makes sure the declaration was fixed before the outcome was known. Install Or from a local checkout: 30-second example What gets recorded Commitment = SHA-256(canonicaljson({agentid, agentversion, p, salt, schema, taskid})) with p as a fixed 6-decimal string, a fresh 128-bit random salt per declaration, sorted keys and no whitespace. Shared test vectors (vectors/commitments.json) are checked by both the Python and the JavaScript implementation. Guarantees and honest limits • A declaration cannot be replaced or re-resolved. Deleting or editing a record breaks the hash chain and verify fails. • Coverage is reported. Declared, resolved and pending are all counted, so you cannot quietly drop the bad ones. Anything unresolved shows as pending. • Timestamps are your local clock.…
Read the full README on GitHub →Remotes
- streamable-http
https://qants-site.qants.workers.dev/mcp
Alternatives to Mizan calibration benchmark
All Mizan calibration benchmark alternatives →Best Legal & Government servers →The most-starred Legal & Government servers in the index, with their live-check result.
| Server | Stars | Last push | Live check |
|---|---|---|---|
| Korean Law MCP | 2,891 | Nov 2026 | Working |
| EdgarTools | 2,859 | Nov 2026 | Local / not checked |
| Global law | 2,167 | Nov 2026 | Working |
| MCP Fiscal Brasil | 433 | Nov 2026 | Local / not checked |
| Legal Data Hunter | 422 | Nov 2026 | Needs sign-in |
Mizan calibration benchmark: questions people ask
- Is Mizan calibration benchmark a remote or a local MCP server?
- According to its entry in the official MCP registry, Mizan calibration benchmark ships as a hosted endpoint (streamable-http) that your client connects to by URL.
- Does Mizan calibration benchmark need an API key?
- Its hosted endpoint completed the Serverdex live check — an MCP initialize + tools/list call — with no credentials on Nov 22, 2026. Individual tools may still ask for a key when called.
- Is Mizan calibration benchmark safe to use?
- Looks healthy: Mizan calibration benchmark is maintained, open source, hosted endpoint answering without a key. In detail — maintained: Active; official registry: Active; source: Open source, MIT; runs: Hosted by the publisher; credentials: None needed to connect. Serverdex check of Nov 22, 2026. This is a reading of the repository, the registry entry and the live check, not a code audit; run the Serverdex security scan on the endpoint before trusting it with real data.
- Is Mizan calibration benchmark still maintained?
- Active: the repository's last commit 2 days ago. Last push Nov 20, 2026, 0 GitHub stars, MIT licence. Read from GitHub on Nov 21, 2026.
- What tools does Mizan calibration benchmark expose?
- 10 tools as listed by the server itself during the live check, including search_agents, get_agent, mizan_pool, mizan_status, mizan_get_passport. The full list with parameters is in the Live check section above.
- How do I add Mizan calibration benchmark to Claude, Cursor or VS Code?
- Copy the config in "Connect this server" into your client's MCP config file (claude_desktop_config.json, ~/.cursor/mcp.json or .vscode/mcp.json), or use the one-click Add to Cursor / Add to VS Code buttons and the one-line commands for Claude Code and Codex; then restart the client.
More from qants-labs
All 2 servers by qants-labs →More Legal & Government servers
Browse all Legal & Government →OCDS German Procurement Search
qune-tech
Search and match German public procurement tenders (OCDS) from your local LLM.
Markbase Trademark Search
Rad-Soft
Search US trademarks, screen proposed names for conflicts, and look up USPTO registration records.
BrokerIA Imoveis
raklapimenta
Search Brazilian real estate, simulate financing, qualify leads, schedule visits.
BrasilAPI (CNPJ, CEP, validation, holidays)
renatoctti
Brazilian public data via BrasilAPI: CNPJ and partners, CEP, CNPJ/CPF validation, holidays
DutyKit
renschrder-stack
EU business duties for AI agents: legal obligations with sources and pre-checks (DE, LU, EU)
Quill — Canadian Government Data (MapleSpike)
reverb256
Canadian government data for AI agents — all jurisdictions, SHA-256 provenance.
Add the badge to your site
Show visitors that Mizan calibration benchmark is listed here — it’s also the link we check for a free listing.
HTML — for your website
<a href="https://serverdex.io/server/io-github-qants-labs-mizan?utm_source=badge"><img src="https://serverdex.io/brand/badge.svg" alt="Mizan calibration benchmark — listed on Serverdex" width="123" height="40" loading="lazy"></a>Recommended. A dofollow link from your own domain is the one that counts for search engines, and it's the link we check for a free listing.
Markdown — for your README
[](https://serverdex.io/server/io-github-qants-labs-mizan?utm_source=badge)Nice for visibility, but GitHub marks README links nofollow, so it doesn't pass authority. Use the HTML badge on your site as well.
Install buttons — for your README
[](https://serverdex.io/install/cursor/io-github-qants-labs-mizan) [](https://serverdex.io/install/vscode/io-github-qants-labs-mizan) [](https://serverdex.io/install/claude-code/io-github-qants-labs-mizan)One click opens Cursor or VS Code with this server's config prefilled; the Claude Code button lands on the one-line command. The links point at Serverdex, so when your config changes the buttons keep working.
Install buttons — HTML for your docs
<a href="https://serverdex.io/install/cursor/io-github-qants-labs-mizan"><img src="https://serverdex.io/brand/install-cursor.svg" alt="Add to Cursor — via Serverdex" width="140" height="28"></a>
<a href="https://serverdex.io/install/vscode/io-github-qants-labs-mizan"><img src="https://serverdex.io/brand/install-vscode.svg" alt="Add to VS Code — via Serverdex" width="147" height="28"></a>
<a href="https://serverdex.io/install/claude-code/io-github-qants-labs-mizan"><img src="https://serverdex.io/brand/install-claude-code.svg" alt="Open in Claude Code — via Serverdex" width="180" height="28"></a>Same buttons as plain links for a docs page or website.
Prefer a live badge with the score, stars and live check? Score badge (links to a page that explains the number and back to this listing).