中文
相关论文

相关论文: MCPTox: A Benchmark for Tool Poisoning Attack on R…

200 篇论文

To reduce development overhead and enable seamless integration between potential components comprising any given generative AI application, the Model Context Protocol (MCP) (Anthropic, 2024) has recently been released and subsequently…

密码学与安全 · 计算机科学 2025-04-14 Brandon Radosevich , John Halloran

Current LLM agents are proficient at calling isolated APIs but struggle with the "last mile" of commercial software automation. In real-world scenarios, tools are not independent; they are atomic, interdependent, and prone to environmental…

人工智能 · 计算机科学 2026-05-21 Yuanyang Li , Xue Yang , Longyue Wang , Weihua Luo , Hongyang Chen

We introduce MCP-Bench, a benchmark for evaluating large language models (LLMs) on realistic, multi-step tasks that demand tool use, cross-tool coordination, precise parameter control, and planning/reasoning for solving tasks. Built on the…

Since the introduction of the Model Context Protocol (MCP), the number of available tools for Large Language Models (LLMs) has increased significantly. These task-specific tool sets offer an alternative to general-purpose tools such as web…

计算与语言 · 计算机科学 2025-12-12 Reza Esfandiarpoor , Vishwas Suryanarayanan , Stephen H. Bach , Vishal Chowdhary , Anthony Aue

Model Context Protocol (MCP) has emerged as a standard interface for connecting LLM agents to external tools. Because MCP servers expose privileged operations such as shell execution, network access, and file-system manipulation to…

密码学与安全 · 计算机科学 2026-05-21 Pengyu Sun , Qishu Jin , Enhao Huang , Zifeng Kang , Xin Liu , Dakun Shen , Song Li

The Model Context Protocol (MCP) introduces a structurally distinct attack surface that existing threat frameworks, designed for traditional software systems or generic LLM deployments, do not adequately cover. This paper presents MCP-38, a…

密码学与安全 · 计算机科学 2026-03-20 Yi Ting Shen , Kentaroh Toyoda , Alex Leung

The Model Context Protocol (MCP) standardizes tool use for LLM-based agents and enable third-party servers. This openness introduces a security misalignment: agents implicitly trust tools exposed by potentially untrusted MCP servers.…

密码学与安全 · 计算机科学 2026-02-25 Zhenhong Zhou , Yuanhe Zhang , Hongwei Cai , Moayad Aloqaily , Ouns Bouachir , Linsey Pang , Prakhar Mehrotra , Kun Wang , Qingsong Wen

The Model Context Protocol (MCP) replaces static, developer-controlled API integrations with more dynamic, user-driven agent systems, which also introduces new security risks. As MCP adoption grows across community servers and major…

密码学与安全 · 计算机科学 2025-11-27 Herman Errico , Jiquan Ngiam , Shanita Sojan

Large Language Models (LLMs) are increasingly serving as autonomous agents, and their utilization of external tools via the Model Context Protocol (MCP) is considered a future trend. Current MCP evaluation sets suffer from issues such as…

人工智能 · 计算机科学 2026-01-22 Wenrui Liu , Zixiang Liu , Elsie Dai , Wenhan Yu , Lei Yu , Tong Yang , Jinjun Han , Hong Gao

The Model Context Protocol (MCP) enables Large Language Models (LLMs) to interact with external tools via tool descriptors, thereby extending their capabilities for task execution, autonomous decision-making, and multi-agent coordination.…

密码学与安全 · 计算机科学 2026-05-22 Saeid Jamshidi , Arghavan Moradi Dakhel , Kawser Wazed Nafi , Foutse Khomh

The Model Context Protocol (MCP) standardizes how a large-language-model (LLM) agent and an external tool server exchange messages, but not trust: a host reads a server's self-declared tool list and dispatches calls, with no notion of which…

密码学与安全 · 计算机科学 2026-05-26 Alfredo Metere

The Model Context Protocol (MCP) is a new and emerging technology that extends the functionality of large language models, improving workflows but also exposing users to a new attack surface. Several studies have highlighted related…

密码学与安全 · 计算机科学 2026-04-14 Tobias Mattsson , Samuel Nyberg , Anton Borg , Ricardo Britto

MCP standardizes how LLMs interact with external systems, forming the foundation for general agents. However, existing MCP benchmarks remain narrow in scope: they focus on read-heavy tasks or tasks with limited interaction depth, and fail…

The rapid proliferation of Model Context Protocol (MCP)-based agentic systems has introduced a new category of security threats that existing frameworks are inadequately equipped to address. We present MCPThreatHive, an open-source platform…

密码学与安全 · 计算机科学 2026-04-16 Yi Ting Shen , Kentaroh Toyoda , Alex Leung

Model Context Protocol (MCP) have quickly become the interface layer between LLM agents and external tools, yet they also introduce unsafe data flows that existing analyzers handle poorly. Vulnerabilities manifest in two directions:…

软件工程 · 计算机科学 2026-05-11 Xinyi Hou , Yanjie Zhao , Haoyu Wang

The Model Context Protocol (MCP) enables large language models (LLMs) to dynamically discover and invoke third-party tools, significantly expanding agent capabilities while introducing a distinct security landscape. Unlike prompt-only…

密码学与安全 · 计算机科学 2026-04-10 Mehrdad Rostamzadeh , Sidhant Narula , Nahom Birhan , Mohammad Ghasemigol , Daniel Takabi

This paper identifies and analyzes a novel vulnerability class in Model Context Protocol (MCP) based agent systems. The attack chain describes and demonstrates how benign, individually authorized tasks can be orchestrated to produce harmful…

密码学与安全 · 计算机科学 2025-08-28 David Noever

The Model Context Protocol (MCP) has emerged as the de facto standard for connecting Large Language Models (LLMs) to external data and tools, effectively functioning as the "USB-C for Agentic AI." While this decoupling of context and…

密码学与安全 · 计算机科学 2025-12-16 Shiva Gaire , Srijan Gyawali , Saroj Mishra , Suman Niroula , Dilip Thakur , Umesh Yadav

The Model Context Protocol has emerged as a transformative standard for connecting large language models to external data sources and tools, rapidly gaining adoption across major AI providers and development platforms. However, existing…

LLMs' capabilities are enhanced by using function calls to integrate various data sources or API results into the context window. Typical tools include search, web crawlers, maps, financial data, file systems, and browser usage, etc.…

人工智能 · 计算机科学 2025-08-12 Shiqing Fan , Xichen Ding , Liang Zhang , Linjian Mo