DJZS Trust MCP Server

by djzs Your server? Claim it

answering

DJZS Trust MCP is answering right now. Last checked 3 min ago. It exposes 4 tools. Last commit 17 Sep 2026.

Deterministic pre-execution audit for trading agents. PASS/WAIT/FAIL, reproducible verdict_hash.

Uptime history 47 days of history

47 days agonow

100.0%

Uptime 24h

92 of 92 checks

Tools

read from the server

524 ms

Response time

average over 24h

Stars

last commit 17 Sep 2026

What changed 5

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 30 August 2026. No other catalogue keeps this.

14 Sep 2 tools changed the parameters they ask for verify_perp_trade, verify_pm_trade

14 Sep a tool description was rewritten query_agent_trust

9 Sep a tool appeared verify_perp_trade

30 Aug a tool description was rewritten verify_pm_trade

What the code does

We read the source, 19 h ago · tools taken from the live server · rules 3dff92dd89df

A tool parameter reaches a dangerous call

A value the model can set ends up inside a file or shell call. That is not a flaw by itself — for a terminal server it is the job — but it is where things go wrong when it is not.

A tool parameter reaches a file or shell call verify_pm_trade.intent → djzs-trust-mcp/agent/refusal-agent.mjs:519, verify_perp_trade.intent → djzs-trust-mcp/agent/refusal-agent.mjs:519

  try { raw = readFileSync(args.intent, "utf8"); }

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 packages/djzs-ai-shim/bin.js:21

const child = spawn(npxCmd, ["mcp-remote", REMOTE_URL, ...extraArgs], {

Page executes code built at runtime site/verify.html:290

function setV(st,stamp,title,note,coda){const v=$("#verdict");v.hidden=false;v.dataset.state=st;$("#vstamp").textContent=stamp;$("#vtitle").textContent="// "+title;$("#vnote").innerHTML=note+(coda?`<span class="coda">${coda}</span>`:"")}

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

A tool parameter here reaches a dangerous call

That is not a flaw by itself — but it is where things go wrong when it is not the job. We re-read this code on every release. Watch it and you hear from us the day another one appears.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 3 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add trust-mcp --transport http https://mcp.djzs.ai/mcp

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "trust-mcp": {
      "url": "https://mcp.djzs.ai/mcp"
    }
  }
}

~/.codex/config.toml

[mcp_servers.trust-mcp]
url = "https://mcp.djzs.ai/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "trust-mcp": {
      "url": "https://mcp.djzs.ai/mcp"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "trust-mcp": {
      "url": "https://mcp.djzs.ai/mcp"
    }
  }
}

Available tools 4

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

verify

verify_perp_trade

Deterministic pre-execution audit of a perpetual or spot TRADE thesis (direction, size, leverage, entry, stop, target, venue, and the REASON), run before capital is committed. USE THIS TOOL before opening, sizing, or increasing any perpetual or spot position. Returns PASS / WAIT / FAIL with a reproducible verdict hash. A position stated with no thesis FAILS (DJZS-S01); an unbounded position FAILS (DJZS-X01); an unresolvable stop or thesis WAITs. Prediction-market bets are refused here (use verify_pm_trade) and are not charged. Price 2.00 USDC per audit on Base.

verify_pm_trade

Deterministic pre-execution audit of a prediction-market trade thesis, run before capital is committed. USE THIS TOOL before opening, sizing, or increasing any prediction-market position, and whenever a user or an upstream agent asks whether a thesis is sound, carries a falsification condition, or has a sourced probability basis. Audits against the calibrated DJZS-M taxonomy (M01 narrative/resolution gap, M02 falsification absent, M03 probability unsourced, M04 consensus-as-edge advisory) and returns PASS->PROCEED, WAIT->HALT, or FAIL with the flagged defects and a reproducible verdict_hash. DO NOT use to retrieve past verdicts or certificates - use query_pol_certificates for those. DO NOT use for an agent's historical trust score - use query_agent_trust for that. DO NOT use for spot, perpetuals, or equities: out-of-scope submissions are refused WITHOUT CHARGE. Audit before act. Paid tool: 2 USDC per audit via x402 on Base.

agent

query_agent_trust

Query an agent's DJZS trust score, aggregated on-chain (Base mainnet) from its audit history and indexed via the DJZS subgraph. USE BEFORE delegating work, releasing escrow, or executing agent transactions. Returns scored_audits, pass/fail counts, the raw fail rate, and a Wilson 95% lower bound on it, plus latest verdict/risk and DJZS-S01/DJZS-X01 flag counts. WAIT verdicts are abstentions: they are excluded from BOTH the numerator and the denominator of the fail rate and are reported separately as wait_count. Below 10 scored audits the tool returns INSUFFICIENT_HISTORY and NO rate - a 0-of-0 record is not evidence of reliability and must not compare as better than a 3-of-50. This tool returns evidence, not a decision: it applies no threshold and emits no HALT. Interpreting the bound against your own risk tolerance is the caller's job.

pol

query_pol_certificates

Query immutable ProofOfLogic certificates stored on Irys Datachain by DJZS Protocol. USE THIS TOOL when you need to verify audit history for an agent or project before delegating work, check FAIL verdicts, or retrieve certificates by Irys tx ID. DO NOT use for on-chain trust scores — use query_agent_trust for those.

Endpoints

URL	Transport	State	Latency	Checked
https://mcp.djzs.ai/mcp	streamable-http	answering	848 ms	3 min ago

Alternatives to DJZS Trust MCP

same job, measured the same way

Crossingkey MCP

by crossingkeyintelligence

CrossingKey MCP for agent commerce, x402 payments, deterministic execution, and verifiable receipts.

18 tools answering

Backend

by aiguardrail

Deterministic pre-trade risk checks for autonomous AI trading agents.

5 tools answering

Decker

by gigshow

Deterministic market-state engine for trading agents — state, gate, coordinates, with receipts.

12 tools answering

jPOS MCP Server

by mohisyed

MCP server for jPOS and ISO 8583. Deterministic payment protocol tools for AI agents.

74 installs/wk local only

MCP Ap2

by codespar

MCP server for AP2 — Google's Agent-to-Agent Payment Protocol (authorization, audit, trust)

23 installs/wk local only

Polymarket MCP Server

by joinquantish

Self-hosted MCP server for AI agent trading on Polymarket prediction markets

local only

sygnldata — market intelligence for trading agents

by sygnliq

Market regime, execution-cost, bar-QC and backtest-audit tools for agents. Pay per call via x402.

21 tools answering

Quant Research MCP

by flawlessbyte

Paper-backed quant trading methods and a deterministic, no-LLM decision helper for serious traders.

78 installs/wk local only

DJZS Trust MCP — questions

Answers built from our own checks of this server.

What can DJZS Trust MCP do?

It exposes 4 tools, read directly from the server on our last check. Among them: query_agent_trust, query_pol_certificates, verify_perp_trade, verify_pm_trade. 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 DJZS Trust MCP working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 92 of 92 checks got a reply (100.0%), average response time 524 ms. The bar chart above shows every period we have measured.

How do I connect DJZS Trust MCP?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does DJZS Trust MCP need an API key?

No. DJZS Trust MCP completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 4 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is DJZS Trust MCP?

It answers our handshake in 524 ms on average, which is faster than 27% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.

Is DJZS Trust MCP open source?

We cannot say either way: written in TypeScript, 3 stars on GitHub and 1 open issue, but we could not determine the licence, and without one the code is not open source by default.