Related papers: MCP Security Bench (MSB): Benchmarking Attacks Aga…
The rapid adoption of foundation models has significantly expanded the capabilities of software systems, enabling them to perform complex language, reasoning, and interaction tasks that were previously difficult to automate. However, this…
Large language model (LLM)-powered agents are increasingly used to plan and execute scientific workflows, yet most research cyberinfrastructure (CI) exposes heterogeneous APIs and implements security models that present barriers for use by…
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…
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…
Explicit modeling of capabilities and skills -- whether based on ontologies, Asset Administration Shells, or other technologies -- requires considerable manual effort and often results in representations that are not easily accessible to…
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…
Large language model (LLM)-based AI agents extend LLM capabilities by enabling access to tools such as data sources, APIs, search engines, code sandboxes, and even other agents. While this empowers agents to perform complex tasks, LLMs may…
The Model Context Protocol (MCP) has emerged as a widely adopted mechanism for connecting large language models to external tools and resources. While MCP promises seamless extensibility and rich integrations, it also introduces a…
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…
The Model Context Protocol (MCP) enhances large language models (LLMs) by integrating external tools, enabling dynamic aggregation of real-time data to improve task execution. However, its non-isolated execution context introduces critical…
The model context protocol (MCP) standardizes how LLMs connect to external tools and data sources, enabling faster integration but introducing new attack vectors. Despite the growing adoption of MCP, existing MCP security studies classify…
Large Language Models (LLMs) are increasingly augmented with external tools through standardized interfaces like the Model Context Protocol (MCP). However, current MCP implementations face critical limitations: they typically require local…
Large Language Models (LLMs) increasingly rely on external tools to perform complex, realistic tasks, yet their ability to utilize the rapidly expanding Model Contextual Protocol (MCP) ecosystem remains limited. Existing MCP research covers…
Industrial automation increasingly requires flexible control strategies that can adapt to changing tasks and environments. Agents based on Large Language Models (LLMs) offer potential for such adaptive planning and execution but lack…
This survey investigates how classical software design patterns can enhance the reliability and scalability of communication in Large Language Model (LLM)-driven agentic AI systems, focusing particularly on the Model Context Protocol (MCP).…
Large language models are increasingly used as orchestrators of external tools via the Model Context Protocol (MCP), but MCP is built for software services with megabytes of memory and does not descend to the microcontrollers that dominate…
We present M^3-Bench, the first benchmark for evaluating multimodal tool use under the Model Context Protocol. The benchmark targets realistic, multi-hop and multi-threaded workflows that require visual grounding and textual reasoning,…
The integration of Large Language Models (LLMs) with Internet-of-Things (IoT) systems faces significant challenges in hardware heterogeneity and control complexity. The Model Context Protocol (MCP) emerges as a critical enabler, providing…
Large language model powered autonomous agents demand robust, standardized protocols to integrate tools, share contextual data, and coordinate tasks across heterogeneous systems. Ad-hoc integrations are difficult to scale, secure, and…
The Model Context Protocol (MCP) has become a widely adopted interface for LLM agents to invoke external tools, yet learned monitoring of MCP tool-call traffic remains underexplored. In this article, the proposed detector is presented as an…