---
title: "Tilburg Researchers Map 73 Ways MCP Servers Silently Break AI Tools"
subtitle: "Researchers analyzed 837 GitHub fault threads across 473 MCP servers to map the 73 distinct ways your AI tool integrations can silently break at runtime"
url: "https://alphasignal.ai/news/tilburg-researchers-map-73-ways-mcp-servers-silently-break-ai-tools"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-06-03T00:00:00.000Z"
updated: "2026-06-11T03:39:42.821Z"
type: "Paper"
topics:
  - "Agents"
  - "Development"
subtopics:
  - "Mcp"
  - "Tool Use"
  - "Code Agents"
  - "Code Agents"
upvotes: 3037
source_url: "https://arxiv.org/abs/2606.05339"
comments: 0
truncated: true
---

# Tilburg Researchers Map 73 Ways MCP Servers Silently Break AI Tools

> Researchers analyzed 837 GitHub fault threads across 473 MCP servers to map the 73 distinct ways your AI tool integrations can silently break at runtime

MCP servers are quietly becoming load-bearing infrastructure for AI applications. When your LLM calls a tool -- querying a database, running code, hitting an API -- it goes through an [MCP server](https://modelcontextprotocol.io/docs/getting-started/intro). And yet, until now, nobody had systematically catalogued how those servers actually fail in production. A new paper from researchers at Tilburg University, the University of Luxembourg, and the University of Naples Federico II changes that, delivering the first empirical taxonomy of runtime faults in MCP servers.

## The M×N Problem MCP Was Built to Solve

Before MCP, connecting AI models to external tools meant writing custom glue code for every model-tool pair. Every AI app needed custom code for every tool, meaning M apps times N tools equals M×N unique integrations to build and maintain. MCP solves this with a unified client-server protocol: MCP enables LLMs to interact with external tools and data sources via a standardized protocol. Each server exposes three primitives -- Tools (callable operations), Resources (contextual data), and Prompts (reusable instruction templates) -- and communicates over JSON-RPC 2.0.

![MCP architecture diagram showing host application, MCP client, and multiple MCP servers connected to external services](https://arxiv.org/html/2606.05339v1/x1.png) 

The problem is that standardizing the interface does not standardize correctness. Rapid adoption in tool-augmented AI workflows has introduced new reliability challenges, such as configuration parameters that are accepted but not enforced at runtime, leading to unintended default behavior. A server can compile cleanly, start up without errors, and still violate the protocol contract mid-session -- and the LLM on the other end has no idea.

## What the Researchers Actually Did

The team did not rely on synthetic benchmarks or theoretical models. They went straight to the source: GitHub issue threads from real MCP server repositories. The pipeline involved several filtering stages to separate genuine MCP runtime faults from generic programming bugs and deployment issues.

1. **Repository collection:** They compiled a dataset from two public sources -- MCP Market and Awesome MCP Servers -- yielding 2,112 entries. After deduplication and validation, the dataset contained 1,774 active, publicly accessible repositories.
2. **Quality filtering:** Repositories were required to have at least 5 contributors, open issues, 100+ commits, and 10+ stars and forks, reducing the set to 473 actively maintained repositories.
3. **Issue mining:** The mining stage produced 78,267 issues and 49,155 pull requests. After merging each issue with its linked pull requests and associated artifacts, they obtained 78,267 consolidated issue-centered threads.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [A Taxonomy of Runtime Faults in Model Context Protocol Servers (arXiv)](https://arxiv.org/html/2606.05339)
- [arXiv abstract page: 2606.05339](https://arxiv.org/abs/2606.05339)
- [Real Faults in Model Context Protocol (MCP) Software: a Comprehensive Taxonomy](https://arxiv.org/html/2603.05637v1)
- [MCP Cheat Sheet (2026) - Model Context Protocol Quick Reference](https://www.webfuse.com/mcp-cheat-sheet)
- [Replication Package on Figshare](https://figshare.com/s/c1e1e802e1b9f38fddf0)
