mcpbeat Sign in

MIZAN · Proof before payment MCP Server

by muaviamohammed Your server? Claim it
answering

MIZAN · Proof before payment is answering right now. Last checked moments ago. It exposes 6 tools. Last commit 30 Oct 2026.

Check before you pay. Prove to get paid. Signed answers on any agent, against your own bar.

The author archived this repository on GitHub, meaning it is no longer maintained.

Uptime history 18 days of history · worst day 54%
18 days agonow
93.5%
Uptime 24h
86 of 92 checks
6
Tools
read from the server
1021 ms
Response time
average over 24h
0
Stars
last commit 30 Oct 2026

What changed 143

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 15 October 2026. No other catalogue keeps this.

28 Oct 4 tool descriptions were rewritten6 times that day check, more, prove and 1 more
28 Oct 4 tools changed the parameters they ask for5 times that day check, more, prove and 1 more
28 Oct 3 tools appeared claim_identity, request_proof, require
24 Oct a tool description was rewritten2 times that day more
23 Oct a tool description was rewritten check
22 Oct a tool changed version7 times that day
22 Oct 3 tool descriptions were rewritten5 times that day check, more, prove
22 Oct a tool changed the parameters it asks for check
21 Oct 42 tools disappeared allocate_check, attempts_lookup, attest_reliance and 39 more
21 Oct 13 tools appeared check, claim_identity, conduct_check and 10 more
and 70 more, back to 15 October 2026

What the code does

We read the source, 1 d ago · tools taken from the live server · rules 995398eba69f

Capabilities

What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.

Runs an external command mizan_agent_tools.py:91
        p = subprocess.run(args, capture_output=True, text=True, timeout=180, cwd=d)

Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.

This code can reach further than it looks

We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.

Three servers free · no card

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 0 min ago.

run in your terminal
claude mcp add mizan --transport http https://studio.mizan.market/mcp
Settings → Connectors → Add custom connector, then paste this address
https://studio.mizan.market/mcp
~/.codex/config.toml
[mcp_servers.mizan]
url = "https://studio.mizan.market/mcp"
.cursor/mcp.json
{
  "mcpServers": {
    "mizan": {
      "url": "https://studio.mizan.market/mcp"
    }
  }
}
.vscode/mcp.json
{
  "servers": {
    "mizan": {
      "type": "http",
      "url": "https://studio.mizan.market/mcp"
    }
  }
}

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

check
check
Call before you pay, hire, or allocate to any agent, service or company. Returns one signed ALLOW or REFUSE, free, valid 24 h, verifiable offline with MIZAN's published key; proceed only on ALLOW. Without a rule, ALLOW needs a passing credential in good standing for the subject (graded PROVEN or RECORDED, stated in the answer; never DECLARED); with a rule, your rule decides, including the lowest grade it accepts. Without a rule, ALLOW says only that a passing record of the claim type in `scope` exists (for example a trading record); it says nothing about other kinds of work, so for a specific job write its bar with require() first. A REFUSE says why (basis: no_record, below_bar, evidence_against or unverifiable); a check never creates a proof request: to ask the counterparty to prove itself, call request_proof(subject, rule). subject = an agent id, a company domain, a service URL (API, MCP or A2A endpoint), a credential id, or a public AI model (model:<org>/<name>, or its huggingface.co URL; a rule about a model's score needs a model subject). rule = a published req_…@v, or the rule require() wrote. bind = {payer, amount, currency, nonce} ties the answer to one payment. Every reply is signed over its whole body (explain and next included) and carries explain and next; errors come back as {error, field, got, reason, fix}, are never an ALLOW and are not signed.
claim
claim_identity
Call once, when you want a record of your own (to get paid or hired, or to be known as a careful buyer). Joins in one call: no account, no email. Returns your agent id and an API key (shown once; keep it), your listing and standing. Checking never needs this; checks stay anonymous. Your page is public only if you choose; leave in one call. Free. Every reply carries explain and next; errors come back as {error, field, got, reason, fix}.
more
more
Call when check, require, prove and claim_identity are not the job: verify a credential someone shows you, the published standard and its gates, the public log and receipts, linking your identifiers, agreements that settle on proof, watching a counterparty. Returns every other tool grouped by job; each is callable at this same address (full list: https://studio.mizan.market/mcp/full). more("problems") gives the problems MIZAN solves. Every reply carries explain and next; errors come back as {error, field, got, reason, fix}.
prove
prove
Call when you want to get paid or hired: counterparties who check you then see a record instead of no_record. Prove the claim, never the method: your model, code and prompts never leave your machine, and every attempt is counted (free private previews included). claim_type trading: one position per bar on a canonical market; a free private verdict first, then (mint=true, with the key from claim_identity) a credential backed by a zero-knowledge proof; minting is free today. Only trading records get a zero-knowledge proof today. claim_type forecast or service: a record MIZAN reads and counts (every forecast, every probe), graded RECORDED; a service endpoint is linked first with link() (see more()). Call with no arguments for the guide and the markets. Every reply carries explain and next; errors come back as {error, field, got, reason, fix}.
request
request_proof
Call when a check says REFUSE (no_record or below_bar) but you still want to pay or hire that counterparty: ask it to prove itself. Creates a proof request for exactly your rule (or MIZAN's default bar), private by default (listed nowhere, reachable only through its link, you anonymous unless show_requester=true), and returns the link plus a ready-to-send message. MIZAN never contacts the counterparty; you send it. When it proves the bar, the request flips to PROVEN and your next check returns ALLOW. Follow it with proof_request_status(request_id) (no key needed), notify_url (a signed webhook, no key), or watch(subject, events, api_key) (needs a key from claim_identity()). The reply says what the bar takes (what_it_takes). Free. Every reply carries explain and next; errors come back as {error, field, got, reason, fix}.
require
require
Call when you know what you need from a counterparty and want it as an exact rule before you check anyone. Write the bar in plain words (words=...) or as structured JSON (rule=..., schema: resource mizan://schemas/requirement-rule-v2.json or https://studio.mizan.market/app/schemas/requirement-rule-v2.schema.json); both give the same rule and the same hash. Returns the exact rule, a read-back in plain English to confirm it means what you meant, its hash, whether it can be published, and suggestions when some words were not understood. Ready-made bars: the library resources (mizan://library/...). Then call check(subject, rule=<the rule>). Free. Every reply carries explain and next; errors come back as {error, field, got, reason, fix}.

Tools removed

Tools this server used to expose. Anything built against them stopped working on the day they went.

allocate_check
removed 21 Oct 2026
attempts_lookup
removed 21 Oct 2026
attest_reliance
removed 21 Oct 2026
bounty
removed 21 Oct 2026
catalogue_markets
removed 21 Oct 2026
check_agent
removed 21 Oct 2026
check_before_you_pay
removed 21 Oct 2026
conduct_check
removed 21 Oct 2026
conformance
removed 21 Oct 2026
credential_status
removed 21 Oct 2026
declare_conduct
removed 21 Oct 2026
endgame
removed 21 Oct 2026
era_history
removed 21 Oct 2026
everything
removed 21 Oct 2026
explain_refusal
removed 21 Oct 2026
exposure_check
removed 21 Oct 2026
forward_commit
removed 21 Oct 2026
list_datasets
removed 21 Oct 2026
list_proven_agents
removed 21 Oct 2026
log_head
removed 21 Oct 2026
log_proof
removed 21 Oct 2026
mint_credential
removed 21 Oct 2026
my_listing
removed 21 Oct 2026
preview_credential
removed 21 Oct 2026
proof_request_status
removed 21 Oct 2026
register_agent
removed 21 Oct 2026
reliance
removed 21 Oct 2026
require_credential
removed 21 Oct 2026
rewards_program
removed 21 Oct 2026
rewards_status
removed 21 Oct 2026
standard_clauses
removed 21 Oct 2026
standard_gates
removed 21 Oct 2026
standing
removed 21 Oct 2026
verdict_receipt
removed 21 Oct 2026
verifier_download
removed 21 Oct 2026
verify_allocate_check
removed 21 Oct 2026
verify_credential
removed 21 Oct 2026
verify_receipt
removed 21 Oct 2026
why_not_gips
removed 21 Oct 2026
work_check
removed 21 Oct 2026

Endpoints

URLTransportStateLatencyChecked
https://studio.mizan.market/mcp streamable-http answering 926 ms 0 min ago

Alternatives to MIZAN · Proof before payment

same job, measured the same way
X402 List MCP
by x402-list

Find and vet x402 payment APIs before your agent pays one: uptime, price, on-chain volume.

118 installs/wk 7 tools answering
x402 Merchant Check
by gradientdecisions

Pre-payment merchant trust checks for x402 agents on Base and Solana.

1 tools answering
Agentic Finance Graph
by agenticfinancegraph

Ledger of AI-agent money on Base: ranked agents, payments, detections, free checks before you pay

25 tools answering
Pulsefeed X402
by nikolife2016

Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.

103 installs/wk 11 tools answering
Boundra — Payment Approval Gateway for AI Agents
by boundra

Allow, ask, or veto — a policy decision point your agent consults before signing any payment

11 tools answering
Payment Guard MCP
by mlawsonking

Pre-send risk check for AI agents that move money — screen an address or payment URL before sending.

94 installs/wk local only
X402 Receipt Verifier
by nexus-mcp-infra

Audits NEXUS's own x402 payment logs against its own delivery logs and issues a signed proof-of-deli

2 tools answering
Agent Wormhole
by runningoffcode

Check tokens, pages and x402 payments before your agent trusts them. Offline verdicts.

136 installs/wk local only

MIZAN · Proof before payment — questions

Answers built from our own checks of this server.

What can MIZAN · Proof before payment do?
It exposes 6 tools, read directly from the server on our last check. Among them: check, claim_identity, more, prove, request_proof, require. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →
Is MIZAN · Proof before payment working right now?
We send a real MCP handshake every 15 minutes. Over the last 24 hours 86 of 92 checks got a reply (93.5%), average response time 1021 ms. The bar chart above shows every period we have measured.
Did MIZAN · Proof before payment ever remove tools?
Yes. allocate_check, attempts_lookup, attest_reliance, bounty and 36 more are no longer exposed — we recorded the date each one disappeared. A tool vanishing usually means a breaking change for anything that depended on it.
Is MIZAN · Proof before payment still maintained?
The author archived this repository on GitHub, meaning it is no longer maintained. We show this because it changes what you can expect: an unmaintained server may keep answering for months and then stop without warning.
How do I connect MIZAN · Proof before payment?
Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.
Does MIZAN · Proof before payment need an API key?
No. MIZAN · Proof before payment completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.
How fast is MIZAN · Proof before payment?
It answers our handshake in 1021 ms on average, which is faster than 5% of all working MCP servers we measure. That is on the slow side — worth knowing if the tool sits inside an interactive loop. The comparison comes from our own checks across the whole registry, every 15 minutes.
Is MIZAN · Proof before payment open source?
The code is open source: it is published under the MIT licence, written in Python and 0 stars on GitHub. The licence covers the code in the repository, not the hosted service at studio.mizan.market, which runs on its operator's own terms.