> 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/issuer/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 clients such as Claude drive the Issuer Service through natural language. It implements the Model Context Protocol (MCP): an MCP server exposes tools and data sources so that an AI client can call them on your behalf. It is not part of the Issuer Service deployment — you run it separately and point it at your issuer instance. ## Issuer-Related Tools The MCP server registers these tools for working with an issuer: ### Schema Management * `create_schema` - Create new credential schemas through natural language * `get_all_schemas` - List all available schemas * `get_schema_by_id` - Retrieve specific schema details * `delete_schema` - Remove unused schemas * `schema_exists_by_type` - Check if a schema type already exists * `get_latest_schema_by_type` - Get the most recent version of a schema ### Credential Issuance * `create_offering` - Generate credential offerings with QR codes Example prompts: ``` "Create a digital ticket schema for my tech conference with fields for event name, date, seat number, and ticket ID." "Show me all the credential schemas available in the system." "Generate a QR code for claiming a concert ticket for the Summer Jazz Festival." ``` ## Setup 1. **Deploy an Issuer Service** via [One-Click Deployment](https://oneclick.empe.io/) 2. **Configure the MCP server** with your issuer's endpoint and credentials: ``` ISSUER_URL=https://your-issuer-instance.example.com ISSUER_API_KEY=your-issuer-api-key ``` 3. **Connect the MCP server** to your AI client (like Claude) The MCP server targets One-Click deployments; for detailed setup instructions and version compatibility, see the [MCP Server repository](https://github.com/empe-io/mcp-server). ## Security Considerations When using the MCP server with production issuer services: * Use dedicated test environments for experimentation * Implement proper access controls for the MCP server * Monitor AI-generated schema and credential operations * Validate all AI-created schemas before production use --- # 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/issuer/mcp-integration.md?ask=&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.