Bridging LLM Agents and Data Spaces: An Architectural Mediation Approach using the Model Context Protocol

连接大模型智能体与数据空间：一种基于模型上下文协议（MCP）的架构中介方法

Abstract: Data Spaces enable sovereign and governed data sharing across organizational boundaries, but their integration with AI agents remains challenging due to mismatches between probabilistic language model interactions and policy-driven data infrastructures.

摘要： 数据空间（Data Spaces）实现了跨组织边界的主权化与受控数据共享，但由于概率性语言模型交互与策略驱动型数据基础设施之间存在不匹配，它们与人工智能智能体的集成仍然面临挑战。

This article presents an architectural mediation approach based on the Model Context Protocol (MCP), implemented through the Eunomia Agent, to enable controlled interaction between large language model (LLM) agents and data space services.

本文提出了一种基于模型上下文协议（Model Context Protocol, MCP）的架构中介方法，并通过 Eunomia 智能体实现，旨在支持大语言模型（LLM）智能体与数据空间服务之间的受控交互。

The proposed mediation layer translates data space capabilities into structured, schema-driven tools that AI agents can discover and invoke while preserving governance constraints.

所提出的中介层将数据空间的功能转化为结构化的、模式驱动的工具，使人工智能智能体能够在遵守治理约束的同时，发现并调用这些工具。

A prototype implementation validates end-to-end interaction across catalog discovery, metadata retrieval, and data service invocation without modifying existing data space components.

原型实现验证了从目录发现、元数据检索到数据服务调用的端到端交互，且无需修改现有的数据空间组件。

Results demonstrate that protocol-based mediation enables interoperable and standards-aligned integration of AI agents into data space ecosystems.

研究结果表明，基于协议的中介机制能够实现人工智能智能体与数据空间生态系统的互操作性及符合标准的集成。

The approach provides practical guidance for organizations seeking to introduce AI-driven automation into governed data-sharing environments while maintaining compliance, interoperability, and architectural separation of concerns.

该方法为寻求在受控数据共享环境中引入人工智能驱动自动化的组织提供了实践指导，同时确保了合规性、互操作性以及架构上的关注点分离。