Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917322444242944 |
|---|---|
| author | Huang, Yuhang Ma, Boyang Yan, Biwei Dai, Xuelong Zhang, Yechao Xu, Minghui Xu, Kaidi Zhang, Yue |
| author_facet | Huang, Yuhang Ma, Boyang Yan, Biwei Dai, Xuelong Zhang, Yechao Xu, Minghui Xu, Kaidi Zhang, Yue |
| contents | The Model Context Protocol (MCP) is an open and standardized interface that enables large language models (LLMs) to interact with external tools and services, and is increasingly adopted by AI agents. However, the security of MCP-based systems remains largely unexplored.In this work, we conduct a large-scale security analysis of MCP servers integrated within MCP clients. We show that treating MCP servers as trusted entities without authenticating the caller identity is fundamentally insecure. Since MCP servers often cannot distinguish who is invoking a request, a single authorization decision may implicitly grant access to multiple, potentially untrusted callers.Our empirical study reveals that most MCP servers rely on persistent authorization states, allowing tool invocations after an initial authorization without re-authentication, regardless of the caller. In addition, many MCP servers fail to enforce authentication at the per-tool level, enabling unauthorized access to sensitive operations.These findings demonstrate that one-time authorization and server-level trust significantly expand the attack surface of MCP-based systems, highlighting the need for explicit caller authentication and fine-grained authorization mechanisms. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07473 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems Huang, Yuhang Ma, Boyang Yan, Biwei Dai, Xuelong Zhang, Yechao Xu, Minghui Xu, Kaidi Zhang, Yue Cryptography and Security Artificial Intelligence The Model Context Protocol (MCP) is an open and standardized interface that enables large language models (LLMs) to interact with external tools and services, and is increasingly adopted by AI agents. However, the security of MCP-based systems remains largely unexplored.In this work, we conduct a large-scale security analysis of MCP servers integrated within MCP clients. We show that treating MCP servers as trusted entities without authenticating the caller identity is fundamentally insecure. Since MCP servers often cannot distinguish who is invoking a request, a single authorization decision may implicitly grant access to multiple, potentially untrusted callers.Our empirical study reveals that most MCP servers rely on persistent authorization states, allowing tool invocations after an initial authorization without re-authentication, regardless of the caller. In addition, many MCP servers fail to enforce authentication at the per-tool level, enabling unauthorized access to sensitive operations.These findings demonstrate that one-time authorization and server-level trust significantly expand the attack surface of MCP-based systems, highlighting the need for explicit caller authentication and fine-grained authorization mechanisms. |
| title | Give Them an Inch and They Will Take a Mile:Understanding and Measuring Caller Identity Confusion in MCP-Based AI Systems |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2603.07473 |