收藏切换
An Empirical Study of Privilege Usage in Large Language Model MCP Servers
收藏切换
Quan Zhang1, Juexiao Feng2, Chijin Zhou1, *, Yu Jiang3
Journal of Computer Research and Development | 2026, 63(5) : 1177 - 1190
Less
收藏切换
Journal of Computer Research and Development | 2026, 63(5): 1177-1190
• Special Issue on Security and Trustworthiness for AI-Enabled Human-Cyber-Physical Systems •
An Empirical Study of Privilege Usage in Large Language Model MCP Servers
Full
Quan Zhang1, Juexiao Feng2, Chijin Zhou1, *, Yu Jiang3
Affiliations
  • 1Shanghai Key Laboratory of Trustworthy Computing (East China Normal University), Shanghai 200062
  • 2China Academy of Industrial Internet, Beijing 100015
  • 3School of Software, Tsinghua University, Beijing 100084
  • born in 1998. PhD, lecturer. His main research interests include intelligent agent security and system security

    born in 1998. PhD. His main research interests include artificial intelligence and intelligent software

    born in 1995. PhD, lecturer. His main research interests include program analysis and system security

    born in 1989. PhD, associate professor, His main research interests include cyber-physical systems and software systems security

About Author:

born in 1998. PhD, lecturer. His main research interests include intelligent agent security and system security

born in 1998. PhD. His main research interests include artificial intelligence and intelligent software

born in 1995. PhD, lecturer. His main research interests include program analysis and system security

born in 1989. PhD, associate professor, His main research interests include cyber-physical systems and software systems security

Published: 2026-05-01 doi: 10.7544/issn1000-1239.202550874
Outline
收藏切换

The evolution of large language models (LLMs) and Model Context Protocol (MCP) has facilitated the development of various MCP servers and tools that extend LLM capabilities, allowing LLMs to interact with external services and content. However, these servers also introduce new security threats. Specifically, they are granted privileges to automate tasks such as email processing and cloud infrastructure management. Due to the inherent instability of LLM outputs and their susceptibility to manipulation, attackers can exploit LLMs to illicitly invoke these tools, causing severe damage. Therefore, the analysis and control of privileges for LLM servers are of paramount importance. This research designs an automated analysis framework to analyze MCP servers and their associated tools. Through static analysis, the framework identifies the privileged APIs called by these tools and their invocation methods. It then categorizes these privileges based on their sensitivity and corresponding behaviors to investigate the current state of privilege usage. We collect 1609 MCP servers and conduct a detailed analysis of 200, revealing that each server requests an average of 40.74 privileged APIs. Furthermore, a significant 52% of these privilege validations rely on API Tokens and passwords, which fail to adhere to the principle of least privilege. This study calls for developers to implement stricter privilege controls for MCP servers and actively explore more secure authorization mechanisms.

large language model  /  Model Context Protocol  /  LLM tools  /  privilege analysis  /  static analysis
张泉, 冯诀宵, 周炽金, 姜宇. 针对大语言模型MCP服务器中权限使用的实证研究. 计算机研究与发展, 2026 , 63 (5) : 1177 -1190 . DOI: 10.7544/issn1000-1239.202550874
Quan Zhang, Juexiao Feng, Chijin Zhou, Yu Jiang. An Empirical Study of Privilege Usage in Large Language Model MCP Servers[J]. Journal of Computer Research and Development, 2026 , 63 (5) : 1177 -1190 . DOI: 10.7544/issn1000-1239.202550874
Year 2026 volume 63 Issue 5
67
31
Cite this Article
BibTeX
Article Info
doi: 10.7544/issn1000-1239.202550874
  • Receive Date:2025-12-05
  • Online Date:2026-11-17
  • Published:2026-05-01
Article Data
Affiliations
History
  • Received:2025-12-05
  • Revised:2026-03-04
Affiliations
    1Shanghai Key Laboratory of Trustworthy Computing (East China Normal University), Shanghai 200062
    2China Academy of Industrial Internet, Beijing 100015
    3School of Software, Tsinghua University, Beijing 100084
References
Share
https://castjournals.cast.org.cn/joweb/jsjyjyfz/EN/10.7544/issn1000-1239.202550874
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family
属数
Number of
genus
种数
Number of
species
占总种数比例
Percentage of
total species (%)
属
Genus
种数
Number of
species
占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT