> For the complete documentation index, see [llms.txt](https://docs.empe.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.empe.io/develop/wallet-server/mcp-integration.md).

# MCP/AI Integration

The Wallet Server's holder API is a good fit for AI agents that need to act as a credential holder. Every operation is a plain, synchronous HTTP call, so it can be exposed as tools in a Model Context Protocol (MCP) server or any other agent framework:

* **Create a holder wallet** — `POST /agent/holder` (choose `did:key` or `did:web`)
* **Process a URI** — `POST /holders/:holderId/process` claims a credential offer or answers a presentation request from QR-code content
* **List stored credentials** — `GET /holders/:holderId/credentials` and `GET /holders/:holderId/credentials/decoded`

## Typical Agent Tasks

* "Create a holder wallet and tell me its DID."
* "Process this credential-offer URI and confirm the credential was stored."
* "Scan the verifier QR and present the matching credential."

## Setup Notes for Agents

* Authenticate with `Authorization: Bearer <JWT>`; the token's `sub` identifies the agent/user and scopes holder ownership
* Keep tokens short-lived; refresh as needed
* Point agents to Swagger UI at `/api-docs` or the OpenAPI JSON at `/api-docs-json` to discover operations

## Local Development

For local development set `AUTH_DISABLED=true`; every request is then treated as an authenticated admin, so no token is needed. Never enable this outside local development.


---

# 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.empe.io/develop/wallet-server/mcp-integration.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.