All news with #mcp tag

🔒 Kiro is now authorized for FedRAMP High and DoD CC SRG Impact Levels 4 and 5 within the AWS GovCloud (US) Regions. This enables federal agencies and public sector organizations with stringent compliance requirements to adopt Kiro for sensitive workloads. Kiro combines an IDE and CLI for agentic AI-driven, spec-driven development, translating prompts into code, documentation, and tests. It also supports native MCP integration to connect with documentation, databases, APIs, and enterprise resources.

🛡️ Cloudflare announced the Cloudflare One stack, a pair of agent skills designed to automate planning, deploying, migrating, and managing Zero Trust environments. The toolkit packages Cloudflare’s institutional migration expertise into two skill files — cloudflare-one and cloudflare-one-migration — to assist with VPN replacement, Gateway policies, connectivity, vendor-to-vendor translation, and troubleshooting. When paired with the Cloudflare code mode MCP server, agents gain typed, controlled access to the Cloudflare API for live inventory, configuration inspection, and curated change workflows.

🔍 Today AWS announced a preview of business context and semantic search for AWS Glue Data Catalog, enabling discovery of data by semantic meaning. You can enrich catalog tables with glossary terms, custom metadata fields, and add skills that provide agents with additional context. The new Glue Search API lets you find tables by both structure and attached business meaning, and MCP-compatible agents can use the aws-data-analytics plugin to integrate with minimal setup.

🔍 AWS Transform for mainframe now provides a connected, traceable reimagine workflow that takes organizations from portfolio assessment through code generation. The service identifies discrete business functions in z/OS COBOL and PL/I workloads, generates development-ready requirements, and produces traceable cloud-native code. Integrations with IDEs such as Kiro via MCP enable requirements and code to flow directly into developer environments with full auditability.

🤝 Today AWS announced general availability of onboarding agents for AWS Partner Central. The agent serves as an always-available advisor that guides new partners through profile setup, verifications, tax and payment setup, compliance, and preparing listings on Marketplace. Partners can interact with the agent in the AWS Partner Central console or programmatically via Model Context Protocol (MCP). The agent auto-populates partner profiles using company website data and provides a personalized roadmap to accelerate readiness to sell with AWS.

🛠️ AWS announces that DevOps Agent now supports custom SRE agents, bring-your-own sub-agents, and headless access via MCP and A2A protocols. These features let teams automate recurring SRE workflows, extend the agent by connecting external sub-agents, and invoke DevOps Agent from familiar tools such as Kiro and Claude. Additional updates include chat enhancements, incident-skip rules, enhanced knowledge with memories and Git-managed skills, human labeling, dashboards for task quality, and availability in five new Regions.

🤝 Amazon Quick now integrates with Snowflake Cortex AI via the Model Context Protocol (MCP), allowing teams to query Snowflake data and documents in natural language and automate multi-step workflows within Quick. After configuring Snowflake's managed MCP server with OAuth, users can query structured data with Cortex Analyst and unstructured documents with Cortex Search. The MCP connection is available across Quick features, including Quick Chat and Flows, and the integration is live in all AWS Regions where Amazon Quick is offered.

🛠️ Amazon OpenSearch Service now integrates MCP Apps to bring observability workflows into compatible agentic IDEs like Claude Desktop and VS Code. With this integration, local AI agents can investigate incidents using logs, traces, metrics, and alerts stored in OpenSearch domains, collections, and Amazon Managed Service for Prometheus. Each MCP App returns both a concise text summary for agent reasoning and an interactive visualization for human review within the same conversation thread.

🚀 Today AWS introduced cross-account and cross-role access for the AWS Model Context Protocol (MCP) Server, part of the Agent Toolkit for AWS. This update lets AI coding agents such as Kiro, Claude Code, or Codex operate across multiple AWS accounts and IAM roles within a single session without restarts. Previously, changing accounts required stopping the session, updating local credentials, and restarting the MCP server; now agents can specify a profile per command. The feature is intended to streamline multi-account workflows and reduce context-switch friction. The MCP Server is available in US East (N. Virginia) and Europe (Frankfurt).

🔧 Today AWS added an interactive wizard to the AWS Command Line Interface that installs and manages the Agent Toolkit for AWS across multiple coding agents. The toolkit provides an MCP server, 40+ agent skills, and plugins to give agents guidance and guardrails. Users can run aws configure agent-toolkit to detect installed agents, choose skills per agent, and search, install, or update skills via the CLI. The MCP Server is available in US East (N. Virginia) and Europe (Frankfurt).

🚀 Google Cloud Storage (GCS) is positioned as the preferred home for large-scale unstructured data and as a foundational component for production AI agents. This post highlights customer examples—Palo Alto Networks and Snap—using GCS as agent memory and analytics storage, and explains how the Model Context Protocol (MCP) enables secure, standardized access. Google offers two MCP server options: a fully managed Remote MCP server for easy, scalable deployments, and a self-managed Local MCP server for custom tooling and transformations, both integrated with Google Cloud security, observability, and tooling.

🔒 Amazon Quick now supports connecting privately hosted Model Context Protocol (MCP) servers via Amazon Virtual Private Cloud (VPC). This enables organizations to integrate proprietary MCP servers running on Amazon EC2, AWS Fargate, AWS Agentcore, or other private compute without exposing them to the public internet. During connector creation, choose your VPC and provide your MCP server URL so teams can interact with private MCPs in Quick while traffic remains routed securely through the VPC.

🛡️ The Remote Model Context Protocol (MCP) Server for AlloyDB is now generally available, providing a secure HTTP endpoint that lets AI agents access real-time operational data. This fully managed service simplifies production deployments by centralizing discovery, offering fine-grained IAM-based authorization, audit logging, and integration with Model Armor for prompt and response protection. Developers can join AlloyDB operational data with analytics in BigQuery and use built-in AI functions for low-latency agentic experiences.

🧭This post explains how A2UI, an open protocol for agent-driven user interfaces, enables agents to return structured JSON UI payloads instead of plain text or HTML. It outlines the four-layer stack (app shell, rendering, conversation pipeline, and cargo), the inline and decoupled patterns, and how Gemini Enterprise integrates a built-in A2UI renderer. The article points to a reference repo, demo, and implementation notes for registering an A2A agent with GE.

🚀 AWS announces Amazon Aurora MySQL-Compatible Edition now integrates with Kiro Powers, enabling developers to build Aurora MySQL-backed applications faster using AI agent assistance. The integration bundles curated Model Context Protocol (MCP) servers, steering files, and hooks validated by Kiro partners to provide immediate expertise in Aurora MySQL operations and schema design via natural language. Developers can execute data plane and control plane tasks conversationally, while task-specific guidance prevents information overload. The feature is available via one-click installation from the Kiro IDE and webpage across all Regions that support Aurora MySQL.

🔧 Data Agent Kit is an open-source toolkit from Google Cloud that brings data engineering and data science skills, plugins, and secure connectors directly into your IDE or CLI. It provides prebuilt agentic skills, Model Context Protocol (MCP) integrations to BigQuery, AlloyDB, and Cloud Storage, plus native extensions for VS Code, Gemini CLI, Claude Code, and Codex. By grounding agents in unified enterprise data, it reduces manual ETL and context-window costs and accelerates intent-driven pipelines; the kit is available in preview.

🔒 This article outlines five architectural patterns for exposing enterprise data to autonomous systems on Google Cloud, using BigQuery examples and mocked CRM data as pedagogical blueprints. It contrasts deterministic, developer-authored SQL APIs with agentic approaches that use LLMs, platform-native reasoning like the Conversational Analytics API, and the vendor-neutral Model Context Protocol (MCP). It highlights trade-offs in trust, complexity, cost, latency, and maintenance.

🚀 Google Cloud announced streaming AI enhancements to its Agentic Data Cloud at Next ‘26, unifying Pub/Sub, Dataflow, BigQuery, Bigtable and Managed Service for Kafka to deliver real-time context and low-latency inference. These additions include Pub/Sub AI inference, BigQuery continuous queries for stateful stream processing, Pub/Sub→Bigtable subscriptions, and unified embedding sinks for immediate semantic search and agent memory. The platform also supports MCP and ADK integrations so agents can manage resources and run inside Dataflow pipelines, reducing context lag for use cases like fraud detection and autonomous supply chain actions.

🛠️ AWS has made its AWS Transform agents available through an agent plugin, a Kiro Power in the Kiro marketplace, and the AWS Transform MCP server. Developers can now invoke transformation capabilities from their IDE, the web console, or programmatically, maintaining consistent job state across surfaces. IAM role authentication is supported, enabling use of existing AWS credentials for environments, workspaces, and jobs.

🔒 Model Context Protocol (MCP), the emerging plugin layer for agentic AI, has become a significant blind spot for security teams, introducing new shadow-AI risks much like shadow IT. CTEM programs can close this gap by extending scoping, discovery, prioritization, validation and mobilization to cover developer workstations, AI toolchains and MCP server configurations. Practical actions include actively enumerating MCP endpoints, scanning agent configuration and markdown context files for hardcoded API keys, and prioritizing exposures by attacker impact to produce actionable remediation tickets for engineering teams.