[2506.02040] Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem

generic · recuperado 2026-09-18 (direct) · original · md
Citado en: 1970182665019039937

Computer Science > Cryptography and Security

arXiv:2506.02040 (cs)

Submitted on 31 May 2025 ([v1), last revised 14 Sep 2025 (this version, v4)]

Title:Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem

Authors:Hao Song, Yiming Shen, Wenxuan Luo, Leixin Guo, Ting Chen, Jiashui Wang, Beibei Li, Xiaosong Zhang, Jiachi Chen

View a PDF of the paper titled Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol (MCP) Ecosystem, by Hao Song and 8 other authors

View PDF

HTML (experimental)

Abstract:

The Model Context Protocol (MCP) is an emerging standard designed to enable seamless interaction between Large Language Model (LLM) applications and external tools or resources. Within a short period, thousands of MCP services have been developed and deployed. However, the client-server integration architecture inherent in MCP may expand the attack surface against LLM Agent systems, introducing new vulnerabilities that allow attackers to exploit by designing malicious MCP servers. In this paper, we present the first end-to-end empirical evaluation of attack vectors targeting the MCP ecosystem. We identify four categories of attacks, i.e., Tool Poisoning Attacks, Puppet Attacks, Rug Pull Attacks, and Exploitation via Malicious External Resources. To evaluate their feasibility, we conduct experiments following the typical steps of launching an attack through malicious MCP servers: upload -> download -> attack. Specifically, we first construct malicious MCP servers and successfully upload them to three widely used MCP aggregation platforms. The results indicate that current audit mechanisms are insufficient to identify and prevent these threats. Next, through a user study and interview with 20 participants, we demonstrate that users struggle to identify malicious MCP servers and often unknowingly install them from aggregator platforms. Finally, we empirically demonstrate that these attacks can trigger harmful actions within the user's local environment, such as accessing private files or controlling devices to transfer digital assets. Additionally, based on interview results, we discuss four key challenges faced by the current MCP security ecosystem. These findings underscore the urgent need for robust security mechanisms to defend against malicious MCP servers and ensure the safe deployment of increasingly autonomous LLM agents.

Subjects:Cryptography and Security (cs.CR); Software Engineering (cs.SE)
Cite as:arXiv:2506.02040 [cs.CR]
(or arXiv:2506.02040v4 [cs.CR] for this version)
https://doi.org/10.48550/arXiv.2506.02040 arXiv-issued DOI via DataCite

Submission history

From: Hao Song [

view email

]

[v1]

Sat, 31 May 2025 08:01:11 UTC (521 KB)

[v2]

Thu, 5 Jun 2025 16:22:09 UTC (521 KB)

[v3]

Wed, 20 Aug 2025 02:42:06 UTC (521 KB)

[v4]

Sun, 14 Sep 2025 07:48:51 UTC (574 KB)

Full-text links:

Access Paper:

view license

Current browse context:

cs.CR

< prev | next >

new | recent | 2025-06

Change to browse by:

cs
cs.SE

References & Citations

Loading...

BibTeX formatted citation

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer ([What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))

Connected Papers Toggle

Connected Papers ([What is Connected Papers?](https://www.connectedpapers.com/about))

Litmaps Toggle

Litmaps ([What is Litmaps?](https://www.litmaps.co/))

scite.ai Toggle

scite Smart Citations ([What are Smart Citations?](https://www.scite.ai/))

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv ([What is alphaXiv?](https://alphaxiv.org/))

Links to Code Toggle

CatalyzeX Code Finder for Papers ([What is CatalyzeX?](https://www.catalyzex.com))

DagsHub Toggle

DagsHub ([What is DagsHub?](https://dagshub.com/))

GotitPub Toggle

Gotit.pub ([What is GotitPub?](http://gotit.pub/faq))

Huggingface Toggle

Hugging Face ([What is Huggingface?](https://huggingface.co/huggingface))

ScienceCast Toggle

ScienceCast ([What is ScienceCast?](https://sciencecast.org/welcome))

Demos

Demos

Replicate Toggle

Replicate ([What is Replicate?](https://replicate.com/docs/arxiv/about))

Spaces Toggle

Hugging Face Spaces ([What is Spaces?](https://huggingface.co/docs/hub/spaces))

Spaces Toggle

TXYZ.AI ([What is TXYZ.AI?](https://txyz.ai))

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower ([What are Influence Flowers?](https://influencemap.cmlab.dev/))

Core recommender toggle

CORE Recommender ([What is CORE?](https://core.ac.uk/services/recommender))

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? **Learn more about arXivLabs**.

Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)

Escrivivir · Scriptorium Skins · Animus Iocandi · Aleph Cero · F.A.R.O. · Material transmedia para agentes del juego ARG · AIGPL · Repositorio