# Import Credential to AI Agent

As per [our instructions](https://docs.cheqd.io/product/getting-started/ai-agents/trust-registry/setup/issue-credential) on issuing a verifiable credential to your AI Agent, you can now use the Agent's DID as the `subjectDID` to create an accreditation for the agent using Cheqd Studio. The response from [Step 4](https://docs.cheqd.io/product/getting-started/ai-agents/setup/issue-credential#step-4-issue-verifiable-credential-to-ai-agent) will include a JWT token in the `proof` section.

Copy the JWT token and ask Claude Desktop (or any your choice of MCP Client) to accept the credential as follows:

> Can you accept the credential from this JWT token "eyJhbGciOiJFZ....."

Claude/Client should use the `import-credential` tool to add this credential to it's wallet as shown below:

<figure><img src="https://3569764573-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FPVAMvpKH7PYzvXA6u6Cn%2Fuploads%2FcESZpAP4TQMv5Hr30x3W%2FScreenshot%202025-05-01%20at%2016.39.07.png?alt=media&#x26;token=85f69f7c-800c-4994-b502-068897a795ab" alt=""><figcaption></figcaption></figure>

## What is happening under the hood?

In the background, Claude is communicating with our MCP Server which relays a request to one of our SDKs, [Credo](https://docs.cheqd.io/product/sdk/credo). Using Credo, the AI Agent imports a Credential into the identity wallet associated with itself.
