# Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomy arXiv: https://arxiv.org/abs/2603.05637 ยท HTML: https://mlsanity.com/paper/2603.05637/ ## Key facts - Cited by 6 papers in the map (data through 14 Oct 2026). - Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. - Builds on 42 of its 183 references that are in the map. - First posted on arXiv 5 Mar 2026. ## Placed in - LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/) ## Builds on (most cited first, 30 of 42) - [Prefix-Tuning: Optimizing Continuous Prompts for Generation](https://mlsanity.com/paper/2101.00190/) (2021) - [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018) - [Calibrate Before Use: Improving Few-Shot Performance of Language Models](https://mlsanity.com/paper/2102.09690/) (2021) - [Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity](https://mlsanity.com/paper/2104.08786/) (2021) - [BERTopic: Neural topic modeling with a class-based TF-IDF procedure](https://mlsanity.com/paper/2203.05794/) (2022) - [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023) - [Large Language Models in Finance: A Survey](https://mlsanity.com/paper/2311.10723/) (2023) - [MMTEB: Massive Multilingual Text Embedding Benchmark](https://mlsanity.com/paper/2502.13595/) (2025) - [FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making](https://mlsanity.com/paper/2407.06567/) (2024) - [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025) - [A survey of agent interoperability protocols: Model Context Protocol (MCP), Agent Communication Protocol (ACP), Agent-to-Agent Protocol (A2A), and Agent Network Protocol (ANP)](https://mlsanity.com/paper/2505.02279/) (2025) - [MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers](https://mlsanity.com/paper/2508.14704/) (2025) - [Gemini Embedding: Generalizable Embeddings from Gemini](https://mlsanity.com/paper/2503.07891/) (2025) - [Taxonomy of Real Faults in Deep Learning Systems](https://mlsanity.com/paper/1910.11015/) (2019) - [Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Servers](https://mlsanity.com/paper/2506.13538/) (2025) - [Bugs in Large Language Models Generated Code: An Empirical Study](https://mlsanity.com/paper/2403.08937/) (2024) - [LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?](https://mlsanity.com/paper/2508.01780/) (2025) - [ScaleMCP: Dynamic and Auto-Synchronizing Model Context Protocol Tools for LLM Agents](https://mlsanity.com/paper/2505.06416/) (2025) - [MCP-AgentBench: Evaluating Real-World Language Agent Performance with MCP-Mediated Tools](https://mlsanity.com/paper/2509.09734/) (2025) - [AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities](https://mlsanity.com/paper/2508.11126/) (2025) - [A Study of LLMs' Preferences for Libraries and Programming Languages](https://mlsanity.com/paper/2503.17181/) (2025) - [LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries](https://mlsanity.com/paper/2508.15760/) (2025) - [Bugs in Machine Learning-based Systems: A Faultload Benchmark](https://mlsanity.com/paper/2206.12311/) (2022) - [Large Language Models for Human-like Autonomous Driving: A Survey](https://mlsanity.com/paper/2407.19280/) (2024) - [Exploring the Problems, their Causes and Solutions of AI Pair Programming: A Study on GitHub and Stack Overflow](https://mlsanity.com/paper/2311.01020/) (2023) - [Predicting Issue Types on GitHub](https://mlsanity.com/paper/2107.09936/) (2021) - [Bug Characterization in Machine Learning-based Systems](https://mlsanity.com/paper/2307.14512/) (2023) - [Failure Modes in LLM Systems: A System-Level Taxonomy for Reliable AI Applications](https://mlsanity.com/paper/2511.19933/) (2025) - [A Taxonomy of Prompt Defects in LLM Systems](https://mlsanity.com/paper/2509.14404/) (2025) - [When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling](https://mlsanity.com/paper/2601.15232/) (2026) ## Built on by (most cited first, 6 of 6) - [Model or Harness? An Interaction-Centric Taxonomy for Localizing Agent Failures](https://mlsanity.com/paper/2607.28802/) (2026) - [When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production LLM Agent Runtime](https://mlsanity.com/paper/2606.14589/) (2026) - [How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests](https://mlsanity.com/paper/2607.21832/) (2026) - [LLM Serving in the Wild: An Empirical Study of Frameworks, Methods, and System Designs](https://mlsanity.com/paper/2608.03036/) (2026) - [A Two-Dimensional Study of the Model Context Protocol: Publication and Adoption](https://mlsanity.com/paper/2609.14721/) (2026) - [MCP Error Messages Written for Developers Hurt the Most Capable Agents Most](https://mlsanity.com/paper/2609.35381/) (2026) ## Abstract (arXiv) The rapid adoption of foundation models has significantly expanded the capabilities of software systems, enabling them to perform complex language, reasoning, and interaction tasks that were previously difficult to automate. However, this progress has also introduced novel challenges that were largely absent in previous generations of software. In particular, the increasing integration of foundation models with external tools and resources raises new concerns regarding reliability, security, and robustness. The Model Context Protocol (MCP) has recently been proposed to standardize interactions between AI-based software systems, software tools, and external resources. Despite its growing adoption, there remains limited systematic understanding of real-world faults in MCP-based software systems. In this paper, we present the first large-scale taxonomy of faults in MCP servers, comprising five high-level fault categories derived from empirical evidence. To evaluate the completeness and generalizability of this taxonomy, we conduct a survey of MCP practitioners with diverse roles and experience levels. The results confirm that all identified fault categories occur in practice and reveal distinct characteristics that differentiate MCP-specific faults from non-MCP faults. Overall, this study provides actionable insights for researchers and practitioners by identifying the most error-prone and critical components of MCP-based systems. These insights can inform the development of more robust, reliable, and secure AI-enabled software systems that rely on MCP.