# Auditing MCP Servers for Over-Privileged Tool Capabilities

arXiv: https://arxiv.org/abs/2603.21641 · HTML: https://mlsanity.com/paper/2603.21641/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Mar 2026.

## Built on by (most cited first, 2 of 2)

- [VIPER-MCP: Detecting and Exploiting Taint-Style Vulnerabilities in Model Context Protocol Servers](https://mlsanity.com/paper/2605.21392/) (2026)
- [Where Is the Tradeoff in Using Third-Party API Routers for Agentic Software Development?](https://mlsanity.com/paper/2607.23624/) (2026)

## Abstract (arXiv)

The Model Context Protocol (MCP) has emerged as a standard for connecting Large Language Models (LLMs) to external tools and data. However, MCP servers often expose privileged capabilities, such as file system access, network requests, and command execution that can be exploited if not properly secured. We present mcp-sec-audit, an extensible security assessment toolkit designed specifically for MCP servers. It implements static pattern matching for Python-based MCP servers and dynamic sandboxed fuzzing and monitoring via Docker and eBPF. The tool detects risky capabilities through configurable rule-based analysis and provides mitigation recommendations.