Designing an MCP Server for Technical Documentation

  • Fachvortrag
  • Künstliche Intelligenz (KI) in der Technischen Kommunikation
  • 10. November
  • 04:45 PM (MEZ) - 05:30 PM (MEZ)
  • Plenum 1
  •  Martin Blumbach

    Martin Blumbach

    • Ericsson

Inhalt

Technical documentation is a valuable enterprise data source. It is nowadays usually provided to AI agents using a Model Context Protocol (MCP) server. In an enterprise context not all use cases can be known, but the goals of AI agents when interacting with technical documentation may not differ so much from the goals of human beings.

We'll present the status of an ongoing project at Ericsson, show how we approach the design of an MCP server for technical documentation, and explain our design decisions for MCP tools, resources, and prompts. We take into account that technical documentation consists not only of documents, but also of structured data (for example configuration parameters, counters, part lists). We'll share what we have learned so far in the hope of triggering a conversation on best practices for designing such MCP servers.

Beside the MCP server itself, we'll look at AI agent skills necessary to use it, and a high level AI knowledge and content strategy to support it.

 

Das lernen Sie

  • AI agents and human beings have similar information needs, but the means to access technical documentation differ
  • How to use the Model Context Protocol (MCP) for technical documentation

Vorkenntnisse

- Basic knowledge of AI agents and the Model Context Protocol (MCP)

- Good understanding of how technical documentation is published 

Referent:in

 Martin Blumbach

Martin Blumbach

  • Ericsson
Biografie

Martin is the lead architect for automating technical documentation of cloud native software products at Ericsson. He is working with knowledge graphs and is making technical documentation available for AI agents. Martin has a long history as system architect of large scale Ericsson products and has over time developed an interest in their information architecture. He enjoys understanding technical concepts and explaining them to humans and AI agents.