A First Measurement Study on Authentication Security in Real-World Remote MCP Servers

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Zhou, Huijun, Zhang, Xiaohan, Zhang, Haozhe, Zhang, Haoyang, Zhang, Mi, Yang, Min
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913152511246336
author Zhou, Huijun
Zhang, Xiaohan
Zhang, Haozhe
Zhang, Haoyang
Zhang, Mi
Yang, Min
author_facet Zhou, Huijun
Zhang, Xiaohan
Zhang, Haozhe
Zhang, Haoyang
Zhang, Mi
Yang, Min
contents The Model Context Protocol (MCP) is emerging as a common interface connecting large language models (LLMs) with external services. Remote deployments are becoming increasingly important as agents connect to user-linked online services, such as social, productivity, and financial services. In such deployments, the authentication boundary between MCP clients and remote servers becomes security-critical, yet remains underexplored. We present the first measurement study of authentication security in real-world remote MCP servers. We identify 7,973 live remote MCP servers, finding that 40.55% expose tools without authentication. Among authenticated servers, OAuth is the dominant authorization mechanism for reaching remote services, and OAuth deployments in the MCP ecosystem commonly exhibit three characteristics: open client environments, dynamic client registration, and delegated authorization. These characteristics distinguish MCP deployments from traditional OAuth and introduce new attack surfaces. Guided by this observation, we derive a taxonomy of authentication flaws comprising three MCP-specific categories and conventional OAuth misconfigurations, for a total of four categories and nine concrete flaw types. To evaluate these flaws at scale, we implement a semi-automated detection framework that combines passive traffic inspection with active dynamic probing. Applying it to 119 testable real-world OAuth-enabled MCP servers, we find that each server exhibits at least one flaw, with a total of 325 flaws identified, among which dynamic client registration flaws affect 96.6% of tested servers. Many of these flaws can lead to sensitive information leakage and account takeover. Through responsible disclosure, we obtained 9 CVE IDs. Our findings expose pervasive authentication weaknesses in the MCP ecosystem and underscore the urgent need for hardened OAuth-based remote deployments.
format Preprint
id arxiv_https___arxiv_org_abs_2605_22333
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A First Measurement Study on Authentication Security in Real-World Remote MCP Servers
Zhou, Huijun
Zhang, Xiaohan
Zhang, Haozhe
Zhang, Haoyang
Zhang, Mi
Yang, Min
Cryptography and Security
The Model Context Protocol (MCP) is emerging as a common interface connecting large language models (LLMs) with external services. Remote deployments are becoming increasingly important as agents connect to user-linked online services, such as social, productivity, and financial services. In such deployments, the authentication boundary between MCP clients and remote servers becomes security-critical, yet remains underexplored. We present the first measurement study of authentication security in real-world remote MCP servers. We identify 7,973 live remote MCP servers, finding that 40.55% expose tools without authentication. Among authenticated servers, OAuth is the dominant authorization mechanism for reaching remote services, and OAuth deployments in the MCP ecosystem commonly exhibit three characteristics: open client environments, dynamic client registration, and delegated authorization. These characteristics distinguish MCP deployments from traditional OAuth and introduce new attack surfaces. Guided by this observation, we derive a taxonomy of authentication flaws comprising three MCP-specific categories and conventional OAuth misconfigurations, for a total of four categories and nine concrete flaw types. To evaluate these flaws at scale, we implement a semi-automated detection framework that combines passive traffic inspection with active dynamic probing. Applying it to 119 testable real-world OAuth-enabled MCP servers, we find that each server exhibits at least one flaw, with a total of 325 flaws identified, among which dynamic client registration flaws affect 96.6% of tested servers. Many of these flaws can lead to sensitive information leakage and account takeover. Through responsible disclosure, we obtained 9 CVE IDs. Our findings expose pervasive authentication weaknesses in the MCP ecosystem and underscore the urgent need for hardened OAuth-based remote deployments.
title A First Measurement Study on Authentication Security in Real-World Remote MCP Servers
topic Cryptography and Security
url https://arxiv.org/abs/2605.22333