PrologMCP: A Standardized Prolog Tool Interface for LLM Agents

Computer Science > Artificial Intelligence [Submitted on 12 Jun 2026] PrologMCP: A Standardized Prolog Tool Interface for LLM Agents Agnieszka Mensfelt, Adarsh Prabhakaran, Adrian Haret, Vince Trencsenyi, Kostas Stathis Frontier reasoning-tuned language models still fail on deductive tasks at depth, and the cost of improved performance through extended internal reasoning scales poorly. Symbolic delegation offers a complementary route: a language model translates the problem, while a solver performs the inference. However, current autoformalization pipelines for logic programming are typically bespoke integrations tied to particular tasks or agents. We introduce PrologMCP, a task-agnostic, open-source server that exposes Prolog as a stateful tool through the Model Context Protocol (MCP). Its compact tool interface, structured error reporting, and per-session isolation make the translate-run-inspect-repair loop a reusable primitive for MCP-capable agents. We evaluate a formalizer agent enhanced with PrologMCP against standard and reasoning LLMs (Claude Sonnet 4.6, GPT-4.1, and o4-mini) on two subsets of PARARULE-Plus: a general-purpose sample and a more challenging one targeting a specific failure mode of natural-language reasoning. On the general sample, the formalizer matches or exceeds reasoning LLMs (accuracy 1.00 vs.\ 1.00 / 0.998), with the largest gains over standard models (0.762 for GPT-4.1). On the challenging subset, the formalizer remains near-perfect (1.00 / 0.99) while reasoning LLMs drop to 0.95 / 0.94. These results suggest that delegating inference to Prolog via MCP is a robust and inspectable alternative to extended natural-language reasoning. Comments: Accepted at Joint Workshop on Statistics and Knowledge Integration for Logic, Learning, Ethical Decisions, and LLMs, 18 July 2026, Lisbon Subjects: Artificial Intelligence (cs.AI) Cite as: arXiv:2606.14935 [cs.AI]   (or arXiv:2606.14935v1 [cs.AI] for this version)   https://doi.org/10.48550/arXiv.2606.14935 Focus to learn more Submission history From: Agnieszka Mensfelt [view email] [v1] Fri, 12 Jun 2026 20:14:51 UTC (275 KB) Access Paper: HTML (experimental) view license Current browse context: cs.AI < prev   |   next > new | recent | 2026-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)