SMCP: Secure Model Context Protocol
Xinyi Hou, Shenao Wang, Yifan Zhang, Ziluo Xue, Yanjie Zhao, Cai Fu, Haoyu Wang

TL;DR
This paper introduces SMCP, an enhanced protocol for agentic AI systems that improves security and privacy by adding identity management, authentication, policy enforcement, and audit logging to the existing Model Context Protocol.
Contribution
The paper presents SMCP, a systematic security extension to MCP, addressing key vulnerabilities and providing a comprehensive framework for secure, reliable agentic AI ecosystems.
Findings
SMCP reduces security risks in agentic AI systems.
It enables robust mutual authentication and policy enforcement.
The protocol supports comprehensive audit logging for accountability.
Abstract
Agentic AI systems built around large language models (LLMs) are moving away from closed, single-model frameworks and toward open ecosystems that connect a variety of agents, external tools, and resources. The Model Context Protocol (MCP) has emerged as a standard to unify tool access, allowing agents to discover, invoke, and coordinate with tools more flexibly. However, as MCP becomes more widely adopted, it also brings a new set of security and privacy challenges. These include risks such as unauthorized access, tool poisoning, prompt injection, privilege escalation, and supply chain attacks, any of which can impact different parts of the protocol workflow. While recent research has examined possible attack surfaces and suggested targeted countermeasures, there is still a lack of systematic, protocol-level security improvements for MCP. To address this, we introduce the Secure Model…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsMulti-Agent Systems and Negotiation · Access Control and Trust · Mobile Agent-Based Network Management
