# Validate AI Agent Trust Chain

> ⚠️ **Before you begin...**
>
> Make sure you have configured the [MCP Client as per the setup instructions](/product/getting-started/ai-agents/trust-registry/setup-mcp.md#getting-started).

To validate your AI Agent, you can simply use the `whois` prompt provided by the Cheqd MCP Server.

<figure><img src="/files/QPs4hiP1NLaXn5EMdUl7" alt=""><figcaption></figcaption></figure>

Then Click "Send" button without writing any other prompt:

<figure><img src="/files/bhRZP45H49wwMVU0klF7" alt=""><figcaption></figcaption></figure>

You can also use `/<mcp-server-name>:whois` if using a CLI client:

<figure><img src="/files/GQYCeiwKmi3bb6ZkELkb" alt=""><figcaption></figcaption></figure>

The response should be similar to below. Claude/Client should use `list-credentials` to get the latest credentials from Agent's wallet, and then use `verify-trust-registry` tool to verify the credential.

<figure><img src="/files/FqWK3OgPQi8TQxtDUF8K" alt=""><figcaption></figcaption></figure>

Then present a summary of the credential:

<figure><img src="/files/y7aCj4P1mHFJ1YYBVexQ" alt=""><figcaption></figcaption></figure>

## Learn more about what's happening under the hood:

Under the hood, the MCP Server is using our trust registry validation engine called TRAIN to recursively verify the issuer of the credential, up to a root of trust.&#x20;

{% hint style="success" %}
If you do not want to use MCP, you can build and validate cheqd Trust Registries in any alternative application using our more generalised tutorials.
{% endhint %}

Read more about our Decentralized Trust Chain (DTC) approach and how TRAIN works below:

<table data-card-size="large" data-view="cards"><thead><tr><th></th><th></th><th></th><th data-hidden data-card-cover data-type="files"></th><th data-hidden data-card-target data-type="content-ref"></th></tr></thead><tbody><tr><td><mark style="color:blue;"><strong>Decentralized Trust Chains (DTCs)</strong></mark></td><td>Build using our Trust Registry solution using DIDs and DID-Linked Resources based on the EBSI Trust Chain model.</td><td></td><td><a href="/files/CGLEPfsyPWvEjCzsSWBD">/files/CGLEPfsyPWvEjCzsSWBD</a></td><td><a href="/pages/DjAIpnb7Gdn2L6yYQMUR">/pages/DjAIpnb7Gdn2L6yYQMUR</a></td></tr><tr><td><mark style="color:blue;"><strong>Get Started With TRAIN</strong></mark></td><td>Deploy TRAIN and start validating trust chains with DNS-anchored roots and cryptographic accreditations.</td><td></td><td><a href="/files/05a3r6gJyicjpoQHWKsB">/files/05a3r6gJyicjpoQHWKsB</a></td><td><a href="/pages/DUOWyjeiy5tfovKyy7O8">/pages/DUOWyjeiy5tfovKyy7O8</a></td></tr></tbody></table>


---

# Agent Instructions: Querying This Documentation

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

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.cheqd.io/product/getting-started/ai-agents/validate.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.