ETDI: Mitigating Tool Squatting and Rug Pull Attacks in Model Context Protocol (MCP) by using OAuth-Enhanced Tool Definitions and Policy-Based Access Control
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916772386439168 |
|---|---|
| author | Bhatt, Manish Narajala, Vineeth Sai Habler, Idan |
| author_facet | Bhatt, Manish Narajala, Vineeth Sai Habler, Idan |
| contents | The Model Context Protocol (MCP) plays a crucial role in extending the capabilities of Large Language Models (LLMs) by enabling integration with external tools and data sources. However, the standard MCP specification presents significant security vulnerabilities, notably Tool Poisoning and Rug Pull attacks. This paper introduces the Enhanced Tool Definition Interface (ETDI), a security extension designed to fortify MCP. ETDI incorporates cryptographic identity verification, immutable versioned tool definitions, and explicit permission management, often leveraging OAuth 2.0. We further propose extending MCP with fine-grained, policy-based access control, where tool capabilities are dynamically evaluated against explicit policies using a dedicated policy engine, considering runtime context beyond static OAuth scopes. This layered approach aims to establish a more secure, trustworthy, and controllable ecosystem for AI applications interacting with LLMs and external tools. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01333 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | ETDI: Mitigating Tool Squatting and Rug Pull Attacks in Model Context Protocol (MCP) by using OAuth-Enhanced Tool Definitions and Policy-Based Access Control Bhatt, Manish Narajala, Vineeth Sai Habler, Idan Cryptography and Security Artificial Intelligence Emerging Technologies The Model Context Protocol (MCP) plays a crucial role in extending the capabilities of Large Language Models (LLMs) by enabling integration with external tools and data sources. However, the standard MCP specification presents significant security vulnerabilities, notably Tool Poisoning and Rug Pull attacks. This paper introduces the Enhanced Tool Definition Interface (ETDI), a security extension designed to fortify MCP. ETDI incorporates cryptographic identity verification, immutable versioned tool definitions, and explicit permission management, often leveraging OAuth 2.0. We further propose extending MCP with fine-grained, policy-based access control, where tool capabilities are dynamically evaluated against explicit policies using a dedicated policy engine, considering runtime context beyond static OAuth scopes. This layered approach aims to establish a more secure, trustworthy, and controllable ecosystem for AI applications interacting with LLMs and external tools. |
| title | ETDI: Mitigating Tool Squatting and Rug Pull Attacks in Model Context Protocol (MCP) by using OAuth-Enhanced Tool Definitions and Policy-Based Access Control |
| topic | Cryptography and Security Artificial Intelligence Emerging Technologies |
| url | https://arxiv.org/abs/2506.01333 |