> 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/for-agents/discovery.md).

# Discovery

Where an agent, a crawler or a registry finds DJZS without being told.

| File           | Address                                       | What it is                                                                                                                                                   |
| -------------- | --------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| llms.txt       | `https://djzs.ai/llms.txt`                    | Plain-text guide for language models. It opens with the free POST.                                                                                           |
| AI Catalog     | `https://djzs.ai/.well-known/ai-catalog.json` | AI Catalog (`specVersion` `"0.9"`) with the MCP server card inline. Served as `application/ai-catalog+json`, CORS open.                                      |
| MCP Registry   | `ai.djzs/trust-mcp`                           | The official MCP Registry entry: remote, streamable HTTP, `https://mcp.djzs.ai/mcp` (`djzs-trust-mcp/server.json`).                                          |
| A2A agent card | `https://mcp.djzs.ai/.well-known/agent.json`  | Agent card for agent-to-agent clients.                                                                                                                       |
| OpenAPI        | `https://mcp.djzs.ai/openapi.json`            | The paid HTTP routes and their payment offers. See the known mismatch on [Paid check over HTTP](https://docs.djzs.ai/for-agents/paid-http.md#contract-file). |
| x402 resources | `https://djzs.ai/.well-known/x402.json`       | The two paid resources with their x402 terms.                                                                                                                |

The djzs.ai home page points to the catalog twice: `<link rel="ai-catalog">` in the page head and a `Link: </.well-known/ai-catalog.json>; rel="ai-catalog"` response header.

## The server card

The catalog entry is `urn:air:djzs.ai:trust-mcp:mcp`, type `application/mcp-server-card+json`, with the card inline:

```json
{
  "$schema": "https://static.modelcontextprotocol.io/schemas/v1/server-card.schema.json",
  "name": "ai.djzs/trust-mcp",
  "version": "1.0.0",
  "title": "DJZS Trade Audit",
  "description": "Checks a prediction-market, perp or spot trade thesis before the order: PASS, WAIT or FAIL.",
  "websiteUrl": "https://djzs.ai",
  "remotes": [{ "type": "streamable-http", "url": "https://mcp.djzs.ai/mcp" }]
}
```

The card also lists the repository and two icons. It validates against the server-card schema of `modelcontextprotocol/ext-server-card` at commit `28db12c`, and its name, version, title, website and icons match what the server reports in `initialize`. Like any server card it is advisory: the live connection is the source of truth.

Two version notes, as of 2026-11-20:

* The AI Catalog is a release candidate. Its spec says implementations use `"0.9"`; the MCP server-card docs show `"1.0"` in their example. The catalog follows the catalog spec and moves to `"1.0"` when that version is published.
* The card does not list protocol versions, because a static file would drift from the server. The server accepts the four listed on [MCP server](https://docs.djzs.ai/for-agents/mcp.md).


---

# 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/for-agents/discovery.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.
