# DJZS Trust MCP

> DJZS Trust MCP, an MCP server by djzs.ai, listed from the official MCP registry. Indexed, not reviewed: facts and our own checks, no score or ranking. Deterministic pre-execution audit for trading agents. PASS/WAIT/FAIL, reproducible verdict_hash.

- Canonical: https://www.anchorterminal.com/tools/djzs-trust-mcp
- Markdown: https://www.anchorterminal.com/tools/djzs-trust-mcp.md (~750 tokens)
- Slim: https://www.anchorterminal.com/tools/djzs-trust-mcp.min.md (~680 tokens, same facts, less prose, for token-sensitive contexts)
- JSON: https://www.anchorterminal.com/tools/djzs-trust-mcp.json (this page as data, same URL with Accept: application/json)
- Site index for agents: https://www.anchorterminal.com/llms.txt (full text: https://www.anchorterminal.com/llms-full.txt)
- API: https://www.anchorterminal.com/api/v1/index.json
- Updated: 2026-10-04

# DJZS Trust MCP

> Indexed, not reviewed: facts from the official MCP registry and our own checks. No score, grade or rank, and not in the rankings until the panel reviews it. How the index works: https://www.anchorterminal.com/indexed/

- Kind: MCP server, by djzs.ai (https://djzs.ai)
- Listed because: It's published in the registry under djzs.ai, a namespace the registry only gives to whoever proves they control that domain.
- What the official MCP registry says: Deterministic pre-execution audit for trading agents. PASS/WAIT/FAIL, reproducible verdict\_hash.

## Facts

- MCP registry: `ai.djzs/trust-mcp` 1.0.0
- Endpoint: https://mcp.djzs.ai/mcp (streamable HTTP)
- Source: https://github.com/SIFR0-dev/djzs-AI
- Website: https://djzs.ai
- GitHub stars: 3
- Registry entry updated: 2026-07-17

## Tools

- Tools it lists (4, about 1,723 tokens of context, `tools/list` without credentials over MCP 2025-11-25, checked 2026-10-04 22:20 UTC):
  - `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…
  - `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,…
  - `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…
  - `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…
- How its tools read to an agent (0 errors, 4 warnings, 1 note, about 1,723 tokens; rules at https://www.anchorterminal.com/check.md; not part of the score):
  - warn TC16 query_agent_trust: no readOnlyHint or destructiveHint
  - warn TC16 query_pol_certificates: no readOnlyHint or destructiveHint
  - warn TC16 verify_perp_trade: no readOnlyHint or destructiveHint
  - warn TC16 verify_pm_trade: no readOnlyHint or destructiveHint
  - note TC24 server: 4 of 4 tools have no outputSchema

- JSON: https://www.anchorterminal.com/api/v1/tools/djzs-trust-mcp.json
- Being indexed says nothing about quality, and nobody can pay for it. Ask for a review: https://www.anchorterminal.com/builders/#claiming