All news with #mcp tag

🔐 The AWS API MCP Server is now available on AWS Marketplace, enabling customers to deploy the Model Context Protocol (MCP) server to Amazon Bedrock AgentCore as a managed offering. The marketplace deployment provides built-in authentication (SigV4 or JWT), session isolation, and simplified container management while enabling configurable IAM roles and network settings to meet enterprise security requirements. Customers also benefit from AgentCore's logging and monitoring capabilities and regional availability where Bedrock AgentCore is supported.

🔎 The AWS Knowledge MCP Server now supports topic-based search across specialized documentation domains, enabling more precise queries against areas such as Troubleshooting, AWS Amplify, AWS CDK, CDK Constructs, and AWS CloudFormation. This enhancement lets MCP clients and agentic frameworks target domain-specific resources to reduce noise and improve relevance. The capability complements existing API reference and general documentation search features and is available immediately at no additional cost, subject to standard rate limits.

🔔 Amazon EKS and ECS now offer fully managed MCP servers in preview, providing a cloud-hosted Model Context Protocol endpoint to enrich AI-powered development and operations. These servers remove local installation and maintenance, and deliver enterprise features such as automatic updates and patching, centralized security via AWS IAM, and audit logging through AWS CloudTrail. Developers can connect AI coding assistants like Kiro CLI, Cursor, or Cline for context-aware code generation and debugging, while operators gain access to a knowledge base of best practices and troubleshooting guidance.

🤖 Anthropic says a China-linked, state-sponsored group used its AI coding tool Claude Code and the Model Context Protocol to mount an automated espionage campaign in mid-September 2025. Dubbed GTG-1002, the operation targeted about 30 organizations across technology, finance, chemical manufacturing and government sectors, with a subset of intrusions succeeding. Anthropic reports the attackers ran agentic instances to carry out 80–90% of tactical operations autonomously while humans retained initiation and key escalation approvals; the company has banned the involved accounts and implemented defensive mitigations.

🔍 AWS announced AWS Capabilities by Region in Builder Center, a web-based tool to discover and compare service availability, features, APIs, and CloudFormation resources across AWS Regions. The interactive interface lets users explore Regions, run side-by-side comparisons, and view forward-looking roadmap details to support global deployment planning. AWS also enhanced the Knowledge MCP Server to expose regional capability data in an LLM-compatible format, enabling MCP clients and agentic frameworks to obtain real-time availability insights and suggested alternatives when features are unavailable.

🚀 Google has open-sourced the GKE Gemini CLI extension, bringing Google Kubernetes Engine directly into the Gemini CLI ecosystem while also functioning as an MCP server for other MCP clients. The extension injects GKE-specific context, tools, and tailored prompts so developers can use shorter, more natural language interactions and integrated slash commands to complete complex workflows. It simplifies common operations—like selecting models and accelerators or generating Kubernetes manifests for inference—while improving compatibility with Cloud Observability. The project is actively maintained with regular releases and community contributions.

🔧 The AWS Serverless Model Context Protocol (MCP) Server now includes specialized tools to configure and manage AWS Lambda event source mappings (ESM), combining AI assistance with ESM expertise. The new toolset—comprising the ESM guidance tool, the ESM optimization tool, and an ESM Kafka troubleshooting tool—translates high-level throughput, latency, and reliability requirements into concrete ESM configurations and generates optimized AWS SAM templates. It also validates VPC network topology for VPC-based event sources and diagnoses common ESM issues to streamline setup, tuning, and troubleshooting workflows.

🔒 Microsoft announced major AI upgrades for Sentinel SIEM and Security Copilot, positioning them as agentic platforms. The update makes Sentinel data lake generally available and introduces public-preview releases of Sentinel graph and the Sentinel Model Context Protocol (MCP) Server so AI agents can access and act on SIEM data. Customers can now build custom agents with natural‑language prompts and discover third‑party agents via a revamped store. Microsoft positions agents to automate investigation and response but warns of increased noise, false positives and a new attack surface.

🧭 The AWS API MCP Server v1.0.0 enables foundation models to interact with AWS APIs via natural language by generating and executing syntactically correct CLI commands. This release reduces startup time and removes local dependencies by converting the suggest_aws_command tool into a remote service, and adds streamable HTTP transport alongside stdio. Security and governance are strengthened with improved secure file system controls, better input validation, configurable denials, and options to require human oversight for mutating actions. Observability is improved through CloudWatch agent log collection, and an experimental get_execution_plan tool (enabled by EXPERIMENTAL_AGENT_SCRIPTS) offers prescriptive workflows; the server is available as a container and open-source on the AWS Labs GitHub repository.

🔎 The AWS Knowledge MCP Server is now generally available, giving AI agents and MCP-compatible clients access to authoritative AWS documentation, blog posts, What's New announcements, and Well-Architected guidance in an LLM-friendly format. The GA release also adds structured knowledge about regional API and CloudFormation resource availability. The server is publicly accessible at no cost and does not require an AWS account, though usage is rate-limited. Configure MCP clients to use the AWS Knowledge MCP Server endpoint to anchor agent responses in trusted AWS context and reduce manual context management.

🔍 Cloudflare is launching a private beta of AI Index, a per-domain, AI‑optimized search index that site owners control and can monetize via Pay per crawl and x402 integrations. The service automatically builds and maintains indexes and exposes standardized APIs — an MCP server, LLMs.txt, a search API, bulk transfer endpoints, and pub/sub subscriptions for real-time updates. It integrates with AI Crawl Control so owners can set access rules or opt out entirely.

🧩 Cloudflare introduces Code Mode, a new approach that converts Model Context Protocol (MCP) tool schemas into a generated TypeScript API so LLMs write code instead of emitting synthetic tool-call tokens. This lets models leverage broad exposure to real-world TypeScript, improving correctness when selecting and composing many or complex tools. Code Mode executes the generated code inside fast, sandboxed Cloudflare Workers isolates that expose only typed bindings to authorized MCP servers, preserving MCP's uniform authorization and discovery while reducing token overhead and orchestration latency.

🔒 A malicious npm package, postmark-mcp, was weaponized to stealthily copy outgoing emails by inserting a hidden BCC in version 1.0.16. The package impersonated an MCP Postmark connector and forwarded every message to an attacker-controlled address, exposing password resets, invoices, and internal correspondence. The backdoor was a single line of code and remained available through regular downloads before the package was removed. Koi Security advises immediate removal, credential rotation, and audits of all MCP connectors.

🔒 A malicious npm package named postmark-mcp was discovered inserting a hidden Bcc that forwarded copies of transactional emails to an attacker-controlled server. Koi Security identified the backdoor in version 1.0.16 after its risk engine flagged suspicious behavior, noting the package had been trusted across many prior releases. With roughly 1,500 weekly downloads, the single-line injection enabled broad exfiltration of password resets, invoices, and internal correspondence before the package was removed; Koi urges immediate removal, credential rotation, and audits of all MCP connectors.

📧 A malicious npm package posing as the official postmark-mcp project quietly added a single line of code to BCC all outgoing emails to an external address. Koi Security found the backdoor in version 1.0.16 after prior releases through 1.0.15 were verified clean. The tainted release was available for about a week and logged roughly 1,500 downloads. Users are advised to remove the package, rotate potentially exposed credentials, and run MCP servers in isolated containers before upgrading.

⚠️ Koi Security has reported that a widely used Model Context Protocol (MCP) implementation, Postmark MCP Server by @phanpak, introduced a malicious change in version 1.0.16 that silently copied emails to an external server. The package, distributed via npm and embedded into hundreds of developer workflows, had more than 1,500 weekly downloads. Users who installed v1.0.16 or later are advised to remove the package immediately and rotate any potentially exposed credentials.

🔧This wrap-up of the Agent Factory series lays out a repeatable blueprint for designing and deploying enterprise-grade AI agents and introduces the agentic web stack. It catalogs eight essential components—communication protocols, discovery, identity and trust, tool invocation, orchestration, telemetry, memory, and governance—and positions Azure AI Foundry as an implementation. The post stresses open standards such as MCP and A2A, emphasizes interoperability across organizations, and highlights observability and governance as core operational requirements.

⚙️ AWS published a Model Context Protocol (MCP) server for AWS IoT SiteWise in the AWS Labs open-source MCP repository to simplify industrial data modeling. The server embeds domain validation and automated modeling, applying correct units, data types, and quality indicators so models are production-ready. It maintains compatibility with existing SiteWise tools and APIs while adding conversational interfaces to streamline model authoring, asset onboarding, and downstream analytics enablement.

🤖 Google introduced the Agent Payments Protocol (AP2), an open standard developed with more than 60 payments and technology firms to enable secure, agent-initiated transactions across platforms. AP2 extends A2A and MCP, using cryptographically-signed Mandates and verifiable credentials to prove authorization, ensure authenticity, and provide a non-repudiable audit trail. The protocol supports cards, real-time bank transfers, and crypto.

🚀 The CrowdStrike Falcon fall release reframes the platform as an Agentic Security Platform, introducing four core innovations: Enterprise Graph, Charlotte AI AgentWorks, the Agent Collaboration framework (powered by MCP), and an AI-native console. Enterprise Graph unifies telemetry into a real-time, AI-ready data layer to give humans and agents shared context. Charlotte AI AgentWorks delivers a no-code environment to design, test, deploy, and govern mission-specific security agents at scale, while MCP enables secure, orchestrated multi-agent collaboration.