Agentic SPARQL: Evaluating SPARQL-MCP-powered Intelligent Agents on the Federated KGQA Benchmark
This work addresses the challenge of combining agentic AI with federated SPARQL querying for knowledge graph applications, representing an incremental advancement over prior automated federation methods.
The paper tackles the problem of enabling intelligent agents to perform federated knowledge graph question answering by integrating SPARQL endpoints with LLMs via the Model Context Protocol, resulting in the implementation and evaluation of different architectural options on an extended benchmark.
Standard protocols such as the Model Context Protocol (MCP) that allow LLMs to connect to tools have recently boosted "agentic" AI applications, which, powered by LLMs' planning capabilities, promise to solve complex tasks with the access of external tools and data sources. In this context, publicly available SPARQL endpoints offer a natural connection to combine various data sources through MCP by (a) implementing a standardised protocol and query language, (b) standardised metadata formats, and (c) the native capability to federate queries. In the present paper, we explore the potential of SPARQL-MCP-based intelligent agents to facilitate federated SPARQL querying: firstly, we discuss how to extend an existing Knowledge Graph Question Answering benchmark towards agentic federated Knowledge Graph Question Answering (FKGQA); secondly, we implement and evaluate the ability of integrating SPARQL federation with LLM agents via MCP (incl. endpoint discovery/source selection, schema exploration, and query formulation), comparing different architectural options against the extended benchmark. Our work complements and extends prior work on automated SPARQL query federation towards fruitful combinations with agentic AI.