# MCP/AI Integration

Wallet Server is ideal for AI agents that need to act as a holder:

* Generate/import DIDs
* Keep a store of credentials
* Run claim/presentation flows from QR content

With a Model Context Protocol (MCP) server or similar agent framework, you can expose Wallet Server operations as tools and drive them via natural language.

## Typical Agent Tasks

* “Create a testnet DID and export its document.”
* “Import this credential and confirm the issuer claim flow.”
* “Scan the verifier QR and present the matching employee credential.”

## Setup Notes for Agents

* Use `Authorization: Bearer <JWT>` with a token whose `sub` identifies the agent/user
* Keep tokens short‑lived; refresh as needed
* Point agents to Swagger `/api-docs` or `/swagger.json` to discover operations

## Local Development

If `ENABLE_DEBUG_SIGN_ENDPOINT=true`:

* `POST /auth/debug/keypair` → create compatible keys and optionally persist to `.env`
* `POST /auth/debug/sign` → mint a JWT for quick testing

Disable debug endpoints in any shared or production environment.


---

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