Connect the gate

DJZS is exposed as a Model Context Protocol server over streamable HTTP at /mcp. The lead tool is verify_pm_trade — the pre-execution audit an agent calls before it acts.

Endpoint: https://djzs-trust-mcp.easy-less-spoil.workers.dev/mcp

Setup // one line

claude mcp add --transport http djzs-trust https://djzs-trust-mcp.easy-less-spoil.workers.dev/mcp

Or via config JSON

For agents that read an MCP server map, register the streamable-HTTP endpoint:

{
  "mcpServers": {
    "djzs-trust": {
      "type": "http",
      "url": "https://djzs-trust-mcp.easy-less-spoil.workers.dev/mcp"
    }
  }
}

Tools // three, one leads

verify_pm_trade — the gate

Pass a free-text prediction-market trade thesis. The tool extracts the reasoning (N=3 consensus), audits it against the calibrated DJZS-M taxonomy, and returns PASS → PROCEED / FAIL / WAIT → HALT with flagged defects and a reproducible verdict_hash. It is prediction-market only: an intent that does not extract as a PM thesis (including the undetermined case) comes back in_scope: false rather than silently running a perpetuals audit.

Response fields: verdict, action, risk_score, flags, unknown_fields, disagreements, verdict_hash, extraction_failsafe, in_scope, and taxonomy versions.

query_pol_certificates

Reads prior ProofOfLogic certificates from the Irys datachain. These are prior-architecture lineage, not output of verify_pm_trade.

query_agent_trust

placeholder Returns pending_subgraph_deploy — the agent trust-score read activates after the DJZS subgraph is deployed, exactly as the code states. Use query_pol_certificates in the meantime.

Taxonomy

The DJZS-M and DJZS-LF taxonomies — code names, severities, and weights — are documented once, as a single source of truth, in the repository README's Taxonomies section: github.com/SIFR0-dev/djzs-AI → Taxonomies. This guide deliberately keeps no local copy — one table, one source.