# A Taxonomy of Runtime Faults in Model Context Protocol Servers arXiv: https://arxiv.org/abs/2606.05339 ยท HTML: https://mlsanity.com/paper/2606.05339/ ## Key facts - Cited by 1 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 29 of its 60 references that are in the map. - First posted on arXiv 3 Jun 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, 29 of 29) - [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020) - [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022) - [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023) - [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021) - [A Survey of Large Language Models](https://mlsanity.com/paper/2303.18223/) (2023) - [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023) - [A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Models](https://mlsanity.com/paper/2401.01313/) (2024) - [Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directions](https://mlsanity.com/paper/2503.23278/) (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) - [On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHub](https://mlsanity.com/paper/2509.14745/) (2025) - [Sampling in Software Engineering Research: A Critical Review and Guidelines](https://mlsanity.com/paper/2002.07764/) (2020) - [Faults in Deep Reinforcement Learning Programs: A Taxonomy and A Detection Approach](https://mlsanity.com/paper/2101.00135/) (2021) - [When MCP Servers Attack: Taxonomy, Feasibility, and Mitigation](https://mlsanity.com/paper/2509.24272/) (2025) - [Defining and Detecting the Defects of the Large Language Model-based Autonomous Agents](https://mlsanity.com/paper/2412.18371/) (2024) - [Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem](https://mlsanity.com/paper/2512.08290/) (2025) - [Bugs in Machine Learning-based Systems: A Faultload Benchmark](https://mlsanity.com/paper/2206.12311/) (2022) - [We Urgently Need Privilege Management in MCP: A Measurement of API Usage in MCP Ecosystems](https://mlsanity.com/paper/2507.06250/) (2025) - [A Measurement Study of Model Context Protocol Ecosystem](https://mlsanity.com/paper/2509.25292/) (2025) - [Failure Diagnosis in Microservice Systems: A Comprehensive Survey and Analysis](https://mlsanity.com/paper/2407.01710/) (2024) - [Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolution](https://mlsanity.com/paper/2501.11709/) (2025) - [What Do Users Ask in Open-Source AI Repositories? An Empirical Study of GitHub Issues](https://mlsanity.com/paper/2303.09795/) (2023) - [muPRL: A Mutation Testing Pipeline for Deep Reinforcement Learning based on Real Faults](https://mlsanity.com/paper/2408.15150/) (2024) - [Practitioners' Expectations on Log Anomaly Detection](https://mlsanity.com/paper/2412.01066/) (2024) - [A Taxonomy of Real Faults in Hybrid Quantum-Classical Architectures](https://mlsanity.com/paper/2502.08739/) (2025) - [Chaos Engineering in the Wild: Findings from GitHub](https://mlsanity.com/paper/2505.13654/) (2025) - [Why Attention Fails: A Taxonomy of Faults in Attention-Based Neural Networks](https://mlsanity.com/paper/2508.04925/) (2025) - [Integrating Large Language Models in Software Engineering Education: A Pilot Study through GitHub Repositories Mining](https://mlsanity.com/paper/2509.04877/) (2025) - [A First Look at the Self-Admitted Technical Debt in Test Code: Taxonomy and Detection](https://mlsanity.com/paper/2510.22409/) (2025) ## Built on by (most cited first, 1 of 1) - [When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production LLM Agent Runtime](https://mlsanity.com/paper/2606.14589/) (2026) ## Abstract (arXiv) MCP (Model Context Protocol) enables LLMs (Large Language Models) to interact with external tools and data sources via a standardized protocol. Its rapid adoption in tool-augmented Artificial Intelligence (AI) workflows has introduced new reliability challenges, such as configuration parameters that are accepted but not enforced at runtime, leading to unintended default behavior, whose runtime fault characteristics remain empirically unexamined. We present the first empirical taxonomy of runtime faults in MCP servers. We manually analyzed 833 confirmed runtime fault threads identified through a repository-mining pipeline covering 473 actively maintained MCP server GitHub repositories and derived a taxonomy using a bottom-up open coding procedure. The taxonomy comprises 11 top-level categories and 27 subcategories (73 leaf fault types), covering recurrent failures across protocol interactions, tool invocations, schema enforcement, state management, model-provider integration, security validation, and timeouts or explicit cancellations of in-progress operations. To assess the taxonomy's external validity, we surveyed 55 MCP server developers. Respondents reported experiencing an average of 20 of the 27 fault subcategories, and no category remained unobserved. These results indicate that the taxonomy reflects widely observed runtime failures in MCP-based systems and shall assist AI software maintenance and evolution in the future.