mlsanityData to 7 Oct 2026

A Taxonomy of Runtime Faults in Model Context Protocol Servers

arXiv 2606.05339 ↗First posted 3 Jun 2026cs.SE cs.AIcited by 1

On the map: LLM agents and tool use → Agent threats, guardrails and governance

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.

Key facts. Cited by 1 paper in the map (data through 7 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.

Builds on

29 of 60 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025Systematization of Knowledge: Security and Safety in the Model Context Protocol Ecosystem9 Dec
  2. 2025A Measurement Study of Model Context Protocol Ecosystem29 Sep

Other references · 27

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  3. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  4. 2021On the Opportunities and Risks of Foundation Modelscited by 3,961
  5. 2023A Survey of Large Language Modelscited by 2,537
  6. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  7. 2024A Comprehensive Survey of Hallucination Mitigation Techniques in Large Language Modelscited by 266
  8. 2025Model Context Protocol (MCP): Landscape, Security Threats, and Future Research Directionscited by 257
  9. 2019Taxonomy of Real Faults in Deep Learning Systemscited by 90
  10. 2025Model Context Protocol (MCP) at First Glance: Studying the Security and Maintainability of MCP Serverscited by 62
  11. 2025On the Use of Agentic Coding: An Empirical Study of Pull Requests on GitHubcited by 53
  12. 2020Sampling in Software Engineering Research: A Critical Review and Guidelinescited by 23
15 more
  1. 2021Faults in Deep Reinforcement Learning Programs: A Taxonomy and A Detection Approachcited by 18
  2. 2025When MCP Servers Attack: Taxonomy, Feasibility, and Mitigationcited by 17
  3. 2022Bugs in Machine Learning-based Systems: A Faultload Benchmarkcited by 15
  4. 2025We Urgently Need Privilege Management in MCP: A Measurement of API Usage in MCP Ecosystemscited by 15
  5. 2024Defining and Detecting the Defects of the Large Language Model-based Autonomous Agentscited by 14
  6. 2024Failure Diagnosis in Microservice Systems: A Comprehensive Survey and Analysiscited by 12
  7. 2025Towards Detecting Prompt Knowledge Gaps for Improved LLM-guided Issue Resolutioncited by 11
  8. 2023What Do Users Ask in Open-Source AI Repositories? An Empirical Study of GitHub Issuescited by 8
  9. 2024muPRL: A Mutation Testing Pipeline for Deep Reinforcement Learning based on Real Faultscited by 5
  10. 2024Practitioners' Expectations on Log Anomaly Detectioncited by 3
  11. 2025A Taxonomy of Real Faults in Hybrid Quantum-Classical Architecturescited by 1
  12. 2025Chaos Engineering in the Wild: Findings from GitHubcited by 1
  13. 2025Why Attention Fails: A Taxonomy of Faults in Attention-Based Neural Networkscited by 1
  14. 2025Integrating Large Language Models in Software Engineering Education: A Pilot Study through GitHub Repositories Miningcited by 1
  15. 2025A First Look at the Self-Admitted Technical Debt in Test Code: Taxonomy and Detectioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production LLM Agent Runtimecited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomy
  2. 2026Description-Code Inconsistency in Real-world MCP Servers: Measurement, Detection, and Security Implications
  3. 2026MCP-in-SoS: Risk assessment framework for open-source MCP servers
  4. 2026Rethinking MCP Security: A Large-Scale Study of Runtime MCP Servers and Security Scanner Reliability
  5. 2026An Empirical Study of Model Context Protocol Applications
  6. 2025MCIP: Protecting MCP Safety via Model Contextual Integrity Protocol
  7. 2026MCP Server Architecture Patterns for LLM-Integrated Applications
  8. 2025A First Look at the Security Issues in the Model Context Protocol Ecosystem