> For the complete documentation index, see [llms.txt](https://docs.djzs.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.djzs.ai/reference/registry-tools.md).

# query\_agent\_trust and query\_pol\_certificates

Two free, read-only MCP tools on `https://mcp.djzs.ai/mcp`. Neither costs anything or writes anything. Source: `djzs-trust-mcp/src/index.ts`.

## query\_agent\_trust

Reads an agent's audit record before you delegate work to it, release escrow, or pay it. The record is written on Base by paid MCP checks that passed `agent_address`, and indexed by the DJZS subgraph.

| Input          | Notes                            |
| -------------- | -------------------------------- |
| `agentAddress` | The agent's `0x` wallet address. |

| Output                                      | Notes                                                                                       |
| ------------------------------------------- | ------------------------------------------------------------------------------------------- |
| `status`                                    | `no_history`, `INSUFFICIENT_HISTORY` (under 10 scored audits: no rate is returned) or `OK`. |
| `total_audits`, `wait_count`                | All recorded checks, and how many were WAIT.                                                |
| `scored_audits`, `pass_count`, `fail_count` | PASS plus FAIL. WAIT is an abstention and is left out of both sides of the rate.            |
| `fail_rate`, `fail_rate_lower_bound_95`     | FAIL over scored audits, and its Wilson 95% lower bound. `null` below 10 scored audits.     |
| `latest_verdict`, `latest_risk_score`       | The most recent check.                                                                      |
| `flag_counts`                               | How often S01 and X01 fired.                                                                |
| `interpretation`                            | How to read the numbers.                                                                    |

The tool returns evidence, not a decision: it applies no threshold and emits no HALT. Its interpretation text suggests, as a starting point only, that a lower bound above 0.3, or S01 or X01 firing more than once, is worth refusing on. Weigh that against your own exposure.

## query\_pol\_certificates

Reads Proof-of-Logic certificates from Irys mainnet: the permanent record every in-scope paid MCP check anchors.

| Input              | Notes                                                                                                                                                                          |
| ------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| `targetSystem`     | Only certificates whose Target-System tag equals this value, exactly.                                                                                                          |
| `verdict`          | `PASS` or `FAIL`.                                                                                                                                                              |
| `tier`             | `micro`, `founder` or `treasury`.                                                                                                                                              |
| `limit`            | 1 to 100, default 20, newest first.                                                                                                                                            |
| `from_ms`, `to_ms` | The search window in Unix milliseconds. Without `from_ms` the server searches the last 14 days, then the last 3 if the wider search fails; set it to reach older certificates. |

A WAIT verdict is not a filter value here; read WAIT history from `query_agent_trust`.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.djzs.ai/reference/registry-tools.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
