The Archive

AgentAM: LLM agent via Model Context Protocol giving process engineers natural-language access to CFD surrogates for laser powder bed fusion optimization.

The Model Context Protocol (MCP) lets agentic AI frameworks connect language models to external tool providers, but it carries attacker-controlled content (tool descriptions, schema fields, and response data) into model context without validation. Prior benchmarks measure model compliance with poisoned instructions without confirming real execution. We present the first cross-framework measurement of MCP tool poisoning with real tool execution. A 25-class root-cause taxonomy unifies prior classifications, and the open-source tool mcpvenom drives a 9,720-cell susceptibility matrix across 12 fr...

MCP-Injector fault-injection framework reveals LLM agent resilience gaps via Model Context Protocol; model scale does not guarantee fault tolerance under realistic tool failures.

Anthropic donates Agent Skills standard to Agentic AI Foundation under Linux Foundation, joining Model Context Protocol as open community standard.

MCPDisCo applies RL to Model Context Protocol agents via Thought-MDP, enabling tool-format skills, server transfer, and cross-server composition.

Simon Willison defends Model Context Protocol (MCP) as valuable for controlled agent deployment, contrasting sandboxed use vs. unrestricted terminal agents.

Google is inviting third-party agents, including Claude and Open Claw, into Google Home. | Photo by Jennifer Pattison Tuohy / The Verge Google is opening up its smart home to AI agents, letting tools like Claude and Open Claw access and control your connected devices and analyze your home's data using the standardized Model Context Protocol. Google Home MCP is a new integration that lets third-party AI agents control and monitor your smart home and act on your behalf. It "allows any AI agents that support MCP, including Google Antigravity, Claude, Hermes or Open Claw, to securely work with al...

CivBench benchmark for long-horizon LLM agents in Civilization VI via Model Context Protocol, spanning 300+ turns and 76 tools.

MCP 2.0 (stateless Model Context Protocol) launches with significant spec changes; Simon Willison revives mcp-explorer and datasette-mcp tooling.

Simon Willison releases llm-mcp-client 0.1a0, enabling Model Context Protocol integration for LLM tools.

Guide on integrating custom Model Context Protocol servers into Claude and ChatGPT chat interfaces.

Euclid-MCP: open-source MCP server coupling LLMs with SWI-Prolog for deterministic logical reasoning in safety-critical domains.

The Model Context Protocol (MCP) is one of the basic building blocks of AI interoperability, giving AI models a secure way to access external data sources and services. It’s the plumbing that lets a chatbot reach into your calendar, your database, or your internal tools, instead of engineers building custom pipes for every connection. Next […]

Training LLMs to orchestrate multi-step tool calls is held back by three coupled obstacles: realistic stateful execution environments are costly to build, synthetic training queries are often detached from the server's actual state (so the generated tool calls fail to execute), and recall-based RL rewards incentivize verbose tool-calling patterns. We present PROVE (Programmatic Rewards On Verified Environments), a framework with three contributions: (1) a library of 20 stateful MCP (Model Context Protocol) servers exposing 343 tools, enabling live-execution RL training with session-scoped sta...

The Model Context Protocol (MCP) has emerged as a transformative standard for connecting large language models (LLMs) with external data sources and tools, and has been rapidly adopted across personal applications and development platforms. However, existing benchmarks predominantly focus on generic information-seeking tools and fail to capture the practical challenges posed by personal social applications, where tools interact with individual accounts or local databases. To bridge this critical gap, we introduce MCP-Persona, the first benchmark specifically designed for evaluating agent perf...

Foundational agent interoperability standards, notably the Agent-to-Agent (A2A) protocol and the Model Context Protocol (MCP), have advanced multi-agent system communication, and complementary identity frameworks leveraging W3C Decentralised Identifiers (DIDs) and Verifiable Credentials (VCs) provide cryptographic agent authentication. However, no existing protocol supports content-based semantic routing of agent payloads across organisational trust boundaries without requiring the routing intermediary to decrypt the payload, which is a hard constraint in compliance-sensitive environments gov...

MCP Server Proto-OKN (mcp-proto-okn) is a Python-based Model Context Protocol server that enables AI assistants to discover, inspect, query and integrate scientific knowledge graphs through natural language. The server provides graph routing, schema inspection, SPARQL execution, ontology expansion, multi-graph querying, and transcript generation, lowering the barrier to cross-domain knowledge graph analysis for biomedical and scientific users. mcp-proto-okn is implemented in Python using the FastMCP framework and is available at https://github.com/sbl-sdsc/mcp-proto-okn. Documentation, client...

Learn how Model Context Protocol works and how enterprises can use MCP to connect AI applications to data, tools, and business systems.

Autonomous AI agents are becoming more capable. Open models, Model Context Protocol (MCP)-connected tools, and portable skills are also making agents easier to... Autonomous AI agents are becoming more capable. Open models, Model Context Protocol (MCP)-connected tools, and portable skills are also making agents easier to extend. But scaling agent use with structural transparency and operational integrity requires more than runtime guardrails. Organizations and teams need to understand and trust the skills, or instructions, an agent is using. Source

MCP-Cosmos integrates world models into Model Context Protocol agents to bridge planning-execution gap via predictive task automation.

Semantic Gateway framework applies formal validation and zero-trust security to LLM-orchestrated enterprise APIs using Model Context Protocol.

Tool Attention framework reduces Model Context Protocol overhead (10k-60k tokens) via dynamic gating and lazy schema loading for LLM agent scaling.

CASCADE proposes three-tier defense architecture against prompt injection and tool poisoning attacks in Model Context Protocol-based LLM systems.

Mistral Studio adds Model Context Protocol support with custom connectors and approval workflows for enterprise data integration.

Anthropic donates Model Context Protocol and establishes Agentic AI Foundation for agent standards.

MCP UI extends the Model Context Protocol to enable AI agents to return fully interactive UI components. It solves the critical challenge that commerce experiences require visual and interactive elements like product selectors, image galleries, and cart flows. This open-source protocol allows agents to embed commerce components while maintaining control through an intent-based messaging system, delivering shopping experiences that go far beyond traditional text-only AI interactions.

You can find the 3-min quickstart from the video here What is MCP? MCP (Model Context Protocol) is a standard way to connect AI models to data sources and tools. It allows AI to access information and capabilities beyond what they were originally trained on. MCP works like a universal connector for AI systems. Just as standard ports let different devices work together, MCP lets different AI models connect to the same tools and data sources. This means developers can build a tool once and have it work with any AI model that supports MCP. It's like the USB-C port of AI applications.

Anthropic introduces Model Context Protocol, a standard for AI agent-tool integration.