#mcp

#mcp

Netskope introduces security capabilities for Model Context Protocol (MCP) communication. The functionality is designed to help organizations deploy AI agents securely. MCP communication enables AI systems to connect to business data and issue autonomous commands. MCP was launched by Anthropic in November 2024 as an open standard for connecting AI agents to external systems. The protocol acts as a universal adapter between AI applications and business assets.

Install the package. Add mock-mcp as a dev dependency inside your project. npm install -D mock-mcp yarn add -D mock-mcp pnpm add -D mock-mcp Configure the Model Context Protocol server. For example, Claude Desktop can launch the binary through npx: Connect from your tests. Use connect to retrieve a mock client and request data for intercepted calls. Run with MCP enabled. Prompt your AI client to run the persistent test command and provide mocks through the tools.

Agents can dynamically discover and invoke external tools or data servers exposed over MCP. Agents can collaborate across runtimes using structured, A2A protocol-driven messaging. Any REST API with an OpenAPI specification can be imported as a callable tool instantly. Agents can run in containers, on-premises, or across multiple clouds, making them portable across environments. The Agent Framework supports a wide

Figma is launching some new updates that allow AI models to directly communicate with its app-building tool and access designs remotely. Figma's Model Context Protocol (MCP) server - a bridge that enables AI models to tap directly into the code behind prototypes and designs created using Figma's tools - has now been expanded to support the design platform's AI prompt-to-app coding tool, Figma Make.

Pega Smart Investigate Agentic Automation promises banks faster and cheaper handling of payment exceptions. These are cases in which payment is not or cannot be made. The updated version primarily adds extra generative AI capabilities to the existing offering. This should lead to better automated handling of cases requiring investigation. Many banks still rely on manual processes to handle cases where payment has not been made. This is despite the growing complexity of the market.

MCP provides a structured interface for tools and AI agents to query observability data, enabling developers to surface traces, metrics, and logs in their IDE without switching context. This high-level capability is designed to streamline debugging and reduce time spent navigating between systems, while also laying the groundwork for consistent access across AI assistants and integrations. Originally launched as an open source project, MCP is now offered by Honeycomb as a managed service.

Move beyond chatbots to build durable MCP servers that run for days, survive failures, and orchestrate elicitations and LLM sampling. Learn remote MCP trade-offs and patterns for Anthony Shaw poses the question: Python has had async for 10 years, so why isn't it more popular? He dives deep on where async is useful and where it is limited. Associated Don't miss Glean's product launch on Sept 25th.

The Linux Foundation has incorporated the open source agentgateway project into its organization. This AI-native proxy has been built from the ground up for AI environments, unlike existing solutions that have been adapted later. The project supports important protocols such as A2A and MCP. Under the wing of the Linux Foundation, agentgateway will have room for organic growth. Neutral governance prevents dependence on individual suppliers. This model has proven itself in other successful open source projects.

One of the most notable updates in this version is the new authentication protocol. It as explained separates the roles of the authentication server and the resource server, making it easier to integrate with widely used standards such as OAuth 2.0 and OpenID Connect. It is stated that the goal is to improve both flexibility and security when managing access to external resources.

The vulnerability allows attackers to trigger arbitrary OS command execution on the machine running mcp-remote when it initiates a connection to an untrusted MCP server, posing a significant risk to users - a full system compromise." Or Peles, JFrog Vulnerability Research Team Leader, said.

MCP isn't truly composable; most composition happens through inference, which affects its effectiveness in coding tasks.

MCP transforms how LLMs interact with Docker, enabling them to execute commands in real-time, facilitating faster DevOps workflows.