Skip to content
AI News HubLIVE
Original source2 min read

PrologMCP: A Standardized Prolog Tool Interface for LLM Agents

Summary

A new paper introduces PrologMCP, an open-source, task-agnostic server that exposes Prolog as a stateful tool through the Model Context Protocol (MCP) for LLM agents. Evaluated on PARARULE-Plus, a formalizer agent with PrologMCP stays near-perfect (1.00/0.99) on a challenging subset where reasoning LLMs drop to 0.95/0.94.

SourcearXiv AIAuthor: Agnieszka Mensfelt, Adarsh Prabhakaran, Adrian Haret, Vince Trencsenyi, Kostas Stathis
PrologMCP: A Standardized Prolog Tool Interface for LLM Agents
Report an error

The correction channel is not available yet. You can copy the article reference below for later.

Correction instructions
Read article

[2606.14935] PrologMCP: A Standardized Prolog Tool Interface for LLM Agents

[Submitted on 12 Jun 2026]

Title:PrologMCP: A Standardized Prolog Tool Interface for LLM Agents

View a PDF of the paper titled PrologMCP: A Standardized Prolog Tool Interface for LLM Agents, by Agnieszka Mensfelt and 4 other authors

View PDF HTML (experimental)

Abstract: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

arXiv-issued DOI via DataCite (pending registration)

Submission history

From: Agnieszka Mensfelt [view email] [v1] Fri, 12 Jun 2026 20:14:51 UTC (275 KB)

Full-text links:

Access Paper:

View a PDF of the paper titled PrologMCP: A Standardized Prolog Tool Interface for LLM Agents, by Agnieszka Mensfelt and 4 other authors

View PDF

HTML (experimental)

TeX Source

view license

Current browse context:

cs.AI

new | recent | 2026-06

Change to browse by:

cs

References & Citations

NASA ADS

Google Scholar

Semantic Scholar

Loading...

Data provided by:

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

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Key points and analysis

Article intelligence

EngineersAdvanced

Key points

  • PrologMCP exposes Prolog as a stateful tool via an open-source, task-agnostic MCP server, making the translate-run-inspect-repair loop a reusable primitive.
  • Its compact tool interface, structured error reporting, and per-session isolation aim to replace bespoke autoformalization pipelines tied to specific tasks or agents.
  • On a general PARARULE-Plus sample, the formalizer matches or beats reasoning LLMs (1.00 vs. 1.00/0.998) and far exceeds standard models (0.762 for GPT-4.1).
  • On a challenging subset, the formalizer stays near-perfect (1.00/0.99) while reasoning LLMs fall to 0.95/0.94, suggesting symbolic delegation is a robust, inspectable alternative.

Highlights and analysis are generated automatically and may contain errors. Check the original source.