> 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/verifier/mcp-integration.md).

# MCP Server Integration

The [Empe MCP Server](https://github.com/empe-io/mcp-server) is an **external companion project**, maintained in its own repository, that lets AI systems like Claude drive verification flows through natural language. It is a Model Context Protocol (MCP) server that exposes verification operations as tools an AI client can call; it is not part of the Verifier Service deployment itself.

## What is MCP?

MCP (Model Context Protocol) servers provide context, tools, and prompts to AI clients, making APIs and data sources accessible to AI systems. The Empe MCP server focuses on Self-Sovereign Identity operations, including verification workflows.

## Available Verifier Tools

The MCP server registers these verifier-related tools:

### Verification Workflows

* `generate_verification_qr` - Create QR codes for credential verification
* `generate_verification_qr_for_vp_query` - Generate QR codes for a specific VP query
* `check_verification_status` - Monitor verification status

### VP Query Management

* `create_vp_query` - Create new Verifiable Presentation queries
* `get_all_vp_queries` - List the VP queries the MCP server manages
* `get_vp_query_by_id` - Retrieve a specific VP query
* `delete_vp_query` - Remove unused VP queries

The MCP server manages its own verification workflow and VP-query records against [One-Click](https://oneclick.empe.io/) deployments; its tools do not map one-to-one onto the Verifier API endpoints documented in this section. See the [repository README](https://github.com/empe-io/mcp-server) for how each tool works.

## Example Prompts

```
"Generate a QR code to verify event tickets for the Annual Developer Conference."

"Create a verification that checks if someone has a MembershipCard credential
with 'Gold' level that hasn't expired yet."

"Check if anyone has scanned the verification QR code I generated earlier."

"Show me all the verification queries we have in the system."
```

## Setup

1. **Deploy a Verifier Service** via [One-Click Deployment](https://oneclick.empe.io/)
2. **Configure external access** (the verifier must be reachable from outside your network)
3. **Set up the MCP server** with your verifier's endpoints and credentials
4. **Connect the MCP server** to your AI client (like Claude)

The MCP server's verifier-related environment variables:

```
VERIFIER_BASE_URL=https://your-verifier-instance.example.com
VERIFIER_CLIENT_URL=https://your-external-accessible-url.com
CLIENT_SECRET=your-verifier-client-secret
SSE_PORT=8080
```

For full setup instructions and compatibility notes, see the [MCP Server repository](https://github.com/empe-io/mcp-server).

## Security Considerations

When using the MCP server with production verifier services:

* Use dedicated test environments for experimentation
* Validate all AI-generated VP queries before production deployment
* Monitor verification requests and results
* Implement proper access controls for the MCP server
* Ensure external verifier URLs use HTTPS and proper authentication


---

# 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/verifier/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.