# MCP-Orchestrated Multi-Agent System for Automated Disinformation Detection

arXiv: https://arxiv.org/abs/2508.10143 · HTML: https://mlsanity.com/paper/2508.10143/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 15 of its 45 references that are in the map.
- First posted on arXiv 13 Aug 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 15 of 15)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [BitFit: Simple Parameter-efficient Fine-tuning for Transformer-based Masked Language-models](https://mlsanity.com/paper/2106.10199/) (2021)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions](https://mlsanity.com/paper/2503.23278/) (2025)
- [A Comprehensive Survey on Applications of Transformers for Deep Learning Tasks](https://mlsanity.com/paper/2306.07303/) (2023)
- [Deciding Fast and Slow: The Role of Cognitive Biases in AI-assisted Decision-making](https://mlsanity.com/paper/2010.07938/) (2020)
- [Where Are the Facts? Searching for Fact-checked Information to Alleviate the Spread of Fake News](https://mlsanity.com/paper/2010.03159/) (2020)
- [A review of possible effects of cognitive biases on the interpretation of rule-based machine learning models](https://mlsanity.com/paper/1804.02969/) (2018)
- [Graph Neural Networks for Text Classification: A Survey](https://mlsanity.com/paper/2304.11534/) (2023)
- [Unlocking Structure Measuring: Introducing PDD, an Automatic Metric for Positional Discourse Coherence](https://mlsanity.com/paper/2402.10175/) (2024)
- [Revisiting Fake News Detection: Towards Temporality-aware Evaluation by Leveraging Engagement Earliness](https://mlsanity.com/paper/2411.12775/) (2024)
- [On the Coherence of Fake News Articles](https://mlsanity.com/paper/1906.11126/) (2019)
- [Knowledge Graph-Driven Retrieval-Augmented Generation: Integrating Deepseek-R1 with Weaviate for Advanced Chatbot Applications](https://mlsanity.com/paper/2502.11108/) (2025)

## Built on by (most cited first, 4 of 4)

- [Multi-Agentic System Leveraging Open-Source LLMs to Mitigate Disinformation Threats](https://mlsanity.com/paper/2606.30259/) (2026)
- [Large Language Models in Misinformation Ecosystems: Misuse, Defense, and Vulnerability](https://mlsanity.com/paper/2607.10402/) (2026)
- [An Explainable Coherence Score for Detecting Temporal Inconsistencies in Political News](https://mlsanity.com/paper/2608.29175/) (2026)
- [Memory-First Fact-Checking: A Knowledge-Graph-Grounded Multi-Agent System for Misinformation Detection](https://mlsanity.com/paper/2608.29617/) (2026)

## Abstract (arXiv)

The large spread of disinformation across digital platforms creates significant challenges to information integrity. This paper presents a multi-agent system that uses relation extraction to detect disinformation in news articles, focusing on titles and short text snippets. The proposed Agentic AI system combines four agents: (i) a machine learning agent (logistic regression), (ii) a Wikipedia knowledge check agent (which relies on named entity recognition), (iii) a coherence detection agent (using LLM prompt engineering), and (iv) a web-scraped data analyzer that extracts relational triplets for fact checking. The system is orchestrated via the Model Context Protocol (MCP), offering shared context and live learning across components. Results demonstrate that the multi-agent ensemble achieves 95.3% accuracy with an F1 score of 0.964, significantly outperforming individual agents and traditional approaches. The weighted aggregation method, mathematically derived from individual agent misclassification rates, proves superior to algorithmic threshold optimization. The modular architecture makes the system easily scalable, while also maintaining details of the decision processes.