Amazon CloudFront introduces a new console experience that simplifies the delivery of secure, high-performance applications to users on the internet. Setting up a content delivery network (CDN) traditionally required deep expertise in CDN configurations, domain management, and security best practices. The new CloudFront console experience streamlines this entire process with a unified approach to content delivery and security. The new experience automatically provisions and manages DNS records with Amazon Route 53 and TLS certificates with AWS Certificate Manager (ACM). Users can now create a secure, optimized distribution in as little as 30 seconds, regardless of their CDN expertise level.
When creating a distribution, CloudFront now automatically applies optimized settings based on your specific origin type. For example, when serving static websites from Amazon S3, CloudFront automatically configures Origin Access Control to prevent direct bucket access, optimizes caching settings for improved performance, and enables recommended security settings – all without requiring you to understand the underlying technical details of these components.
This new onboarding experience makes it easier for you to leverage AWS’ global edge network, reduce latency for your end users, and enhance the security posture of your applications. The new experience is available globally at no additional cost. To get started with the new CloudFront experience, visit the Amazon CloudFront console or check out our documentation.
Amazon CloudFront introduces a new console experience that simplifies the delivery of secure, high-performance applications to users on the internet. Setting up a content delivery network (CDN) traditionally required deep expertise in CDN configurations, domain management, and security best practices. The new CloudFront console experience streamlines this entire process with a unified approach to content delivery and security. The new experience automatically provisions and manages DNS records with Amazon Route 53 and TLS certificates with AWS Certificate Manager (ACM). Users can now create a secure, optimized distribution in as little as 30 seconds, regardless of their CDN expertise level. When creating a distribution, CloudFront now automatically applies optimized settings based on your specific origin type. For example, when serving static websites from Amazon S3, CloudFront automatically configures Origin Access Control to prevent direct bucket access, optimizes caching settings for improved performance, and enables recommended security settings – all without requiring you to understand the underlying technical details of these components. This new onboarding experience makes it easier for you to leverage AWS’ global edge network, reduce latency for your end users, and enhance the security posture of your applications. The new experience is available globally at no additional cost. To get started with the new CloudFront experience, visit the Amazon CloudFront console or check out our documentation.
AWS Compute Optimizer now detects idle EC2 Auto Scaling groups using G and P instance types, enabling you to identify additional savings opportunities in your AWS spend. As AI development accelerates, organizations are creating more Auto Scaling groups with G and P instance types for training and inference workloads. Once you enable the NVIDIA CloudWatch agent, Compute Optimizer analyzes utilization data and identifies groups that have completed jobs and remained idle during your specified lookback period, making it easier to identify and prevent waste on these high-cost instance types.
This new feature is available in all AWS Regions where AWS Compute Optimizer is available except for the AWS GovCloud (US) and the China Regions. The new recommendations will also be available in Cost Optimization Hub. For more information about Compute Optimizer, visit our product page and documentation. You can start using AWS Compute Optimizer through the AWS Management Console, AWS Services CLI, or AWS SDK.
AWS Compute Optimizer now detects idle EC2 Auto Scaling groups using G and P instance types, enabling you to identify additional savings opportunities in your AWS spend. As AI development accelerates, organizations are creating more Auto Scaling groups with G and P instance types for training and inference workloads. Once you enable the NVIDIA CloudWatch agent, Compute Optimizer analyzes utilization data and identifies groups that have completed jobs and remained idle during your specified lookback period, making it easier to identify and prevent waste on these high-cost instance types. This new feature is available in all AWS Regions where AWS Compute Optimizer is available except for the AWS GovCloud (US) and the China Regions. The new recommendations will also be available in Cost Optimization Hub. For more information about Compute Optimizer, visit our product page and documentation. You can start using AWS Compute Optimizer through the AWS Management Console, AWS Services CLI, or AWS SDK.
AWS Network Firewall now supports native integration with AWS Transit Gateway for simplified deployment and management of network security across your global AWS infrastructure. This capability is available in 5 AWS Regions, allowing customers to implement security controls more efficiently.
AWS Transit Gateway interconnects your Amazon Virtual Private Clouds (VPCs) and on-premises networks, while AWS Network Firewall provides comprehensive security controls for those VPCs. Native attachment simplifies connecting these services, providing centralized security control without complex VPC configurations. Additionally, you can configure one or multiple Availability Zones (AZs) for high availability, maintaining traffic flow within the same AZ.
This integration is available in the following AWS Regions: Africa (Cape Town), Asia Pacific (Hyderabad), Europe (Stockholm), Europe (Zurich), and Middle East (UAE). There are no additional charges for this native integration beyond standard pricing of AWS Network Firewall and AWS Transit Gateway.
To get started, visit the AWS Network Firewall service documentation.
AWS Network Firewall now supports native integration with AWS Transit Gateway for simplified deployment and management of network security across your global AWS infrastructure. This capability is available in 5 AWS Regions, allowing customers to implement security controls more efficiently. AWS Transit Gateway interconnects your Amazon Virtual Private Clouds (VPCs) and on-premises networks, while AWS Network Firewall provides comprehensive security controls for those VPCs. Native attachment simplifies connecting these services, providing centralized security control without complex VPC configurations. Additionally, you can configure one or multiple Availability Zones (AZs) for high availability, maintaining traffic flow within the same AZ. This integration is available in the following AWS Regions: Africa (Cape Town), Asia Pacific (Hyderabad), Europe (Stockholm), Europe (Zurich), and Middle East (UAE). There are no additional charges for this native integration beyond standard pricing of AWS Network Firewall and AWS Transit Gateway. To get started, visit the AWS Network Firewall service documentation.
Amazon RDS for MySQL now supports community MySQL Innovation Release 9.3 in the Amazon RDS Database Preview Environment, allowing you to evaluate the latest Innovation Release on Amazon RDS for MySQL. You can deploy MySQL 9.3 in the Amazon RDS Database Preview Environment which provides the benefits of a fully managed database, making it simpler to set up, operate, and monitor databases.
MySQL 9.3 is the latest Innovation Release from the MySQL community. MySQL Innovation releases include bug fixes, security patches, as well as new features. MySQL Innovation releases are supported by the community until the next innovation minor, whereas MySQL Long Term Support (LTS) Releases, such as MySQL 8.0 and MySQL 8.4, are supported by the community for up to eight years. Please refer to the MySQL 9.3 release notes and Amazon RDS MySQL release notes for more details.
Amazon RDS Database Preview Environment supports both Single-AZ and Multi-AZ deployments on the latest generation of instance classes. Amazon RDS Database Preview Environment database instances are retained for a maximum of 60 days and are automatically deleted after the retention period. Amazon RDS database snapshots created in the Preview Environment can only be used to create or restore database instances within the Preview Environment.
Amazon RDS for MySQL now supports community MySQL Innovation Release 9.3 in the Amazon RDS Database Preview Environment, allowing you to evaluate the latest Innovation Release on Amazon RDS for MySQL. You can deploy MySQL 9.3 in the Amazon RDS Database Preview Environment which provides the benefits of a fully managed database, making it simpler to set up, operate, and monitor databases. MySQL 9.3 is the latest Innovation Release from the MySQL community. MySQL Innovation releases include bug fixes, security patches, as well as new features. MySQL Innovation releases are supported by the community until the next innovation minor, whereas MySQL Long Term Support (LTS) Releases, such as MySQL 8.0 and MySQL 8.4, are supported by the community for up to eight years. Please refer to the MySQL 9.3 release notes and Amazon RDS MySQL release notes for more details. Amazon RDS Database Preview Environment supports both Single-AZ and Multi-AZ deployments on the latest generation of instance classes. Amazon RDS Database Preview Environment database instances are retained for a maximum of 60 days and are automatically deleted after the retention period. Amazon RDS database snapshots created in the Preview Environment can only be used to create or restore database instances within the Preview Environment. Amazon RDS Database Preview Environment database instances are priced the same as production RDS instances created in the US East (Ohio) Region. For further information, see Working with the Database Preview Environment. To get started with the Preview Environment from the RDS console, navigate here.
Amazon S3 now includes additional context in HTTP 403 Access Denied errors for requests made to resources in accounts within the same AWS Organization. This context includes the type of policy that denied access, the reason for denial, and information on the AWS Identity and Access Management (IAM) user or role that requested access to the resource. This context helps you to troubleshoot access issues, identify the root cause of access denied errors, and fix incorrect access controls by updating the relevant policies. This additional context is also available in AWS CloudTrail logs.
Enhanced access denied error messages are rolling out in the coming weeks in all AWS Regions. To learn more about how to troubleshoot access denied errors in S3, visit the S3 User Guide and the IAM troubleshooting documentation.
Amazon S3 now includes additional context in HTTP 403 Access Denied errors for requests made to resources in accounts within the same AWS Organization. This context includes the type of policy that denied access, the reason for denial, and information on the AWS Identity and Access Management (IAM) user or role that requested access to the resource. This context helps you to troubleshoot access issues, identify the root cause of access denied errors, and fix incorrect access controls by updating the relevant policies. This additional context is also available in AWS CloudTrail logs. Enhanced access denied error messages are rolling out in the coming weeks in all AWS Regions. To learn more about how to troubleshoot access denied errors in S3, visit the S3 User Guide and the IAM troubleshooting documentation.
Microsoft como cliente cero: Empoderar a los equipos de investigación con IA
Por: Ryen White, director de investigación de socios, Microsoft Research.
La investigación siempre ha sido una parte integral de la identidad de Microsoft, que impulsa nuestro papel como líder tecnológico global. Desde 1991, Microsoft Research se ha dedicado a un enfoque de investigación fundamental: avanzar en el conocimiento, profundizar nuestra comprensión del mundo y explorar cómo la tecnología puede empoderar a las personas y las organizaciones. A través de su extenso cuerpo de publicaciones y el compromiso de compartir de manera abierta su trabajo, Microsoft Research continúa la colaboración con la comunidad de investigación global para impulsar avances en IA y más allá. Juntos, ampliamos los límites de lo que es posible para extender la capacidad humana, crear valor para nuestros clientes y ofrecer un amplio beneficio social.
Transformación de la investigación con IA en Microsoft Research
Con Microsoft a la cabeza de la carga en IA, los equipos de investigación de Microsoft están a la vanguardia, a través de nuestra experiencia, de fomentar el liderazgo intelectual e impulsar la innovación en IA e investigación. La IA está en el centro de muchos de los proyectos pioneros de Microsoft Research, desde ayudar a los investigadores a analizar conjuntos de datos masivos en cuestión de segundos, inventar nuevas soluciones de IA que beneficiarían a la humanidad y colaborar con la comunidad investigadora global a través del programa Accelerating Foundation Models Research (AFMR).
Microsoft Research se encuentra en una posición única en la que no solo puede adoptar y utilizar la IA, sino también inventar la IA. Hemos realizado importantes inversiones en IA, a través de la creación de nuevos métodos, modelos y tecnologías de IA. Para infundir la IA más a profundidad en el proceso de investigación, se lleva a cabo una iniciativa experimental que ayuda a los equipos a moverse más rápido, pensar en grande y compartir de manera más efectiva. Esta iniciativa se divide en tres estrategias clave: usar, infundir y difundir la IA en toda la organización.
El uso de la IA (herramientas y operaciones) se centra en optimizar el acceso y el avance de la IA.
Infundir IA (Investigación y Desarrollo) consiste en maximizar el potencial de la IA para revolucionar los procesos de investigación.
La difusión de la IA (conectividad y flujo de información) garantiza el intercambio rápido de conocimientos, herramientas y aprendizajes de IA con otras personas, tanto dentro como fuera de Microsoft Research.
El objetivo no es solo adoptar la IA, sino aumentar y reinventar la forma en que se realiza la investigación, para empoderar a todos los miembros de la organización para que logren más.
La integración de la IA en los procesos de investigación en Microsoft Research proporciona información valiosa para los investigadores y las empresas. El uso de la IA puede acelerar los ciclos de innovación, mejorar la eficiencia operativa y conducir al desarrollo de herramientas y productos de vanguardia. Estos avances ponen de manifiesto cómo la IA puede reinventar los flujos de trabajo tradicionales, agilizar las operaciones e impulsar el crecimiento y la rentabilidad, convirtiéndola en un foco estratégico para que las organizaciones la implementen.
GraphRAG: Avanzar en la investigación con grafos de conocimiento
GraphRAG es un sistema modular de generación aumentada de recuperación (RAG, por sus siglas en inglés) basado en gráficos que utiliza grandes modelos de lenguaje para crear gráficos de conocimiento a partir de texto sin procesar. Esta técnica mejora el rendimiento de los modelos de lenguaje de gran tamaño en conjuntos de datos privados al proporcionar datos estructurados y resúmenes, lo que facilita a los investigadores la extracción de información significativa a partir de datos complejos.
Los cambios que ocurren en la IA en este momento, son en verdad sorprendentes. Las capacidades se expanden muy rápido. Lo veo como una especie de acelerador. Todo lo que hacemos en investigación, podemos hacerlo más rápido, podemos hacer más preguntas, y todo esto ha sido una especie de velocidad de vértigo.
—Nathan Evans, arquitecto principal de software de Microsoft Research
Data Formulator: Transformación de los datos en información
Data Formulator es una herramienta innovadora diseñada para ayudar a los investigadores a explorar y analizar datos más rápido. Mediante el uso de IA, Data Formulator permite a los usuarios crear visualizaciones enriquecidas sin necesidad de amplios conocimientos de programación. Esta herramienta combina IA y enfoques interactivos para comunicar la intención de visualización, lo que hace que el análisis de datos sea más accesible y eficiente
La IA en verdad acelera nuestro proceso de experimentación. En el pasado, necesitábamos hacer un montón de hacking durante semanas para experimentar con los diseños. Pero ahora podemos tener un pensamiento de alto nivel, podemos hacer el prototipo en un corto período de tiempo, y podemos empezar a pensar sobre eso.
—Chenglong Wang, investigador senior de Microsoft Research
Aceleración de la investigación de modelos de base: democratización de la investigación en IA
El programa Accelerating Foundation Models Research (AFMR) proporciona a los investigadores académicos acceso a modelos de cimentación de última generación alojados en Microsoft Azure a través de los servicios de IA de Microsoft Azure. Esta iniciativa fomenta una red global de investigación en IA y ofrece modelos sólidos y confiables que ayudan a avanzar en la investigación en disciplinas que van desde el descubrimiento científico y la educación hasta la atención médica, el empoderamiento multicultural, el trabajo legal y el diseño.
El programa AFMR trabaja con la comunidad de investigación académica en general para explorar diferentes aspectos de los modelos de fundación para lograr tres objetivos:
Objetivo 1: Alinear la IA con los objetivos, valores y preferencias humanos compartidos
Esto implica mejorar la seguridad, la solidez, la sostenibilidad, la responsabilidad y la transparencia de los modelos de IA. Un proyecto notable alineado con este objetivo es «ERBench: Un punto de referencia de alucinación verificable de manera automática basado en entidades-relaciones para grandes modelos de lenguaje.” Para este proyecto, los investigadores crearon ERBench, que ayuda a evaluar y mejorar la precisión y fiabilidad del contenido generado por IA. Esto garantiza que los modelos de IA se alineen con los valores humanos y reduce el riesgo de desinformación.
Objetivo 2: Mejorar las interacciones entre la IA y los seres humanos
El segundo objetivo se centra en mejorar las interacciones entre la IA y los humanos para aumentar la confianza, el ingenio humano, la creatividad y la productividad, al tiempo que se reduce el riesgo de desarrollar una IA perjudicial para las personas y la sociedad. El proyecto «A medida que los modelos generativos mejoran, las personas adaptan sus indicaciones» explora cómo los estímulos cambian a medida que mejoran los modelos de IA generativa. Los resultados mostraron que los participantes que utilizaron modelos más avanzados produjeron indicaciones mejores, más largas y más descriptivas. Esta investigación proporciona información valiosa sobre la dinámica cambiante entre los humanos y la IA, lo que ayuda a crear sistemas de IA más intuitivos y efectivos.
Objetivo 3: Acelerar el descubrimiento científico
El tercer objetivo es acelerar el descubrimiento científico a través del descubrimiento proactivo de conocimiento, la generación de hipótesis y la generación de datos multimodales. Un proyecto que ejemplifica este objetivo exploró «Copilotos basados en inteligencia artificial para generar evidencia causal«. En esta iniciativa, se exploraron grandes modelos de lenguaje como «copilotos» causales para ayudar a identificar fallas en los diseños de estudios médicos. Estos modelos podrían ayudar a los investigadores al proporcionar orientación experta en el diseño de los estudios, para mejorar la precisión de las conclusiones extraídas de los estudios.
La IA es en verdad importante en la investigación porque tiene el potencial, el enorme potencial para acelerar la investigación, que es necesaria para abordar algunos de los mayores desafíos de hoy y mañana.
La próxima frontera: mirar hacia el futuro de la IA en la investigación
A medida que la investigación científica evoluciona en una era impulsada por la IA y las tecnologías en la nube, las oportunidades para la innovación, la colaboración y el impacto global no tienen precedentes. Desde la aceleración de los descubrimientos científicos hasta la mejora de la alineación entre humanos y agentes, los modelos de fundación remodelan la forma en que se realiza, comparte y escala la investigación. De cara al futuro, los investigadores y las instituciones no solo deben adoptar estas herramientas, sino también construir marcos sólidos para su adopción y evaluación.
Todavía nos queda mucho por explorar sobre cómo podemos avanzar en la investigación en Microsoft y este es apenas el comienzo.
AWS announces an official source for AWS API Model definition files and service model packages, providing developers with access to API definitions for all AWS services. We now publish daily updates of these API models to an open-source GitHub repository in Smithy format and also publish these packages to Maven Central.
AWS public service models enable developers to take advantage of the same service model definitions that AWS uses for live services. These API models can be pulled into integrated development environments using the new packages available in Maven and can be used for developer tools use cases like mock testing or evolving MCP server needs. By utilizing open source Smithy code generators, you can also generate purpose-built AWS SDKs.
AWS announces an official source for AWS API Model definition files and service model packages, providing developers with access to API definitions for all AWS services. We now publish daily updates of these API models to an open-source GitHub repository in Smithy format and also publish these packages to Maven Central. AWS public service models enable developers to take advantage of the same service model definitions that AWS uses for live services. These API models can be pulled into integrated development environments using the new packages available in Maven and can be used for developer tools use cases like mock testing or evolving MCP server needs. By utilizing open source Smithy code generators, you can also generate purpose-built AWS SDKs. The AWS service API models can be found on GitHub and Maven. Learn more in our AWS News blog post.
Today, AWS announces that AWS Control Tower supports seven new compliance frameworks in Control Catalog. Control Catalog is the central place in AWS for searching and enabling managed controls.In addition to existing frameworks, controls are now mapped to CIS-v8.0, FedRAMP-r4, ISO-IEC-27001:2013-Annex-A, NIST-CSF-v1.1, NIST-SP-800-171-r2, PCI-DSS-v4.0, SSAE-18-SOC-2-Oct-2023.
To get started, navigate to the Control Catalog in AWS Control Tower and search for a framework like PCI-DSS-v4.0 to view related controls. This feature helps you meet your compliance requirements faster and with higher confidence. For programmatic access, utilize the new ListControlMappings API to search controls by frameworks, and take advantage of the updated ListControls and GetControl APIs, which now support GovernedResources, to understand the resource types governed by each control. We’ve also introduced a new classification system to help you better comprehend and manage controls. In addition to the new frameworks, controls in Control Catalog are now mapped to a domain (e.g., «Data Protection»), an objective (e.g., «Data Encryption»), and a common control (e.g., «Encrypt data at rest»). This clearer structure simplifies the process of understanding, searching, and deploying the controls you need. If you’re using AWS Config, now you’ll see the same comprehensive mapping of Config rules to compliance frameworks, domains, objectives, and common controls that you find in AWS Control Tower, ensuring a unified experience across your AWS environment.
You can use Control Catalog with new mappings in all AWS Regions where AWS Control Tower is available, including AWS GovCloud (US). To learn more, visit AWS Control Tower User Guide.
Today, AWS announces that AWS Control Tower supports seven new compliance frameworks in Control Catalog. Control Catalog is the central place in AWS for searching and enabling managed controls.In addition to existing frameworks, controls are now mapped to CIS-v8.0, FedRAMP-r4, ISO-IEC-27001:2013-Annex-A, NIST-CSF-v1.1, NIST-SP-800-171-r2, PCI-DSS-v4.0, SSAE-18-SOC-2-Oct-2023. To get started, navigate to the Control Catalog in AWS Control Tower and search for a framework like PCI-DSS-v4.0 to view related controls. This feature helps you meet your compliance requirements faster and with higher confidence. For programmatic access, utilize the new ListControlMappings API to search controls by frameworks, and take advantage of the updated ListControls and GetControl APIs, which now support GovernedResources, to understand the resource types governed by each control. We’ve also introduced a new classification system to help you better comprehend and manage controls. In addition to the new frameworks, controls in Control Catalog are now mapped to a domain (e.g., «Data Protection»), an objective (e.g., «Data Encryption»), and a common control (e.g., «Encrypt data at rest»). This clearer structure simplifies the process of understanding, searching, and deploying the controls you need. If you’re using AWS Config, now you’ll see the same comprehensive mapping of Config rules to compliance frameworks, domains, objectives, and common controls that you find in AWS Control Tower, ensuring a unified experience across your AWS environment. You can use Control Catalog with new mappings in all AWS Regions where AWS Control Tower is available, including AWS GovCloud (US). To learn more, visit AWS Control Tower User Guide.
AWS Key Management Service (KMS) now supports the FIPS 203 Module-Lattice Digital Signature Standard (MLDSA), a quantum-resistant digital signature algorithm designed to help organizations address emerging quantum computing threats. This post-quantum signature algorithm is one of the selected algorithms standardized by NIST to protect sensitive information well into the foreseeable future, including after the advent of cryptographically relevant quantum computers. ML-DSA is particularly valuable for manufacturers and developers who need to protect firmware and application code signing where cryptographic signatures cannot be easily updated after deployment and for organizations that require signatures on digital content to remain valid for several years.
The ML-DSA keys integrate with the existing KMS CreateKey and Sign APIs, enabling customers to preserve their established automation processes, IAM and KMS key policies, auditing capabilities, and tagging workflows. AWS KMS support for ML-DSA introduces three new key specs (ML_DSA_44, ML_DSA_65, and ML_DSA_87) that work with the post-quantum SigningAlgorithm ML_DSA_SHAKE_256, with support for both raw signatures and the pre-hashed variant (External Mu).
AWS Key Management Service (KMS) now supports the FIPS 203 Module-Lattice Digital Signature Standard (MLDSA), a quantum-resistant digital signature algorithm designed to help organizations address emerging quantum computing threats. This post-quantum signature algorithm is one of the selected algorithms standardized by NIST to protect sensitive information well into the foreseeable future, including after the advent of cryptographically relevant quantum computers. ML-DSA is particularly valuable for manufacturers and developers who need to protect firmware and application code signing where cryptographic signatures cannot be easily updated after deployment and for organizations that require signatures on digital content to remain valid for several years. The ML-DSA keys integrate with the existing KMS CreateKey and Sign APIs, enabling customers to preserve their established automation processes, IAM and KMS key policies, auditing capabilities, and tagging workflows. AWS KMS support for ML-DSA introduces three new key specs (ML_DSA_44, ML_DSA_65, and ML_DSA_87) that work with the post-quantum SigningAlgorithm ML_DSA_SHAKE_256, with support for both raw signatures and the pre-hashed variant (External Mu).
This new feature is generally available and you can use ML-DSA in the following AWS Regions: US West (N. California), and Europe (Milan) with the remaining commercial AWS Regions to follow in the coming days. To learn more, see the AWS Security Blog for how to create post-quantum signatures using AWS KMS and ML-DSA, and see the ML-DSA signing topic in the AWS KMS Developer Guide.
Today, Amazon Q Developer announced support for Model Context Protocol (MCP) in the integrated development environment (IDE) plugins, enabling developers to utilize external tools to support richer contextual, development workflows. MCP is an open protocol that standardizes how AI models can, in a secure and structured way, access external tools, data sources, and APIs.
You can now augment the list of built-in tools with any MCP server that supports the stdio transport layer. MCP servers can be managed within the Q Developer user interface, making it easy to add or remove servers, and modify tool permissions. By extending your IDE, Q Developer is able to provide more customized responses by orchestrating tasks across native and MCP server-based tools.
MCP support is available within the Visual Studio Code and JetBrains IDE plugins, and Amazon Q Developer CLI. To get started, visit the Amazon Q Developer documentation or read the blog to learn more.
Today, Amazon Q Developer announced support for Model Context Protocol (MCP) in the integrated development environment (IDE) plugins, enabling developers to utilize external tools to support richer contextual, development workflows. MCP is an open protocol that standardizes how AI models can, in a secure and structured way, access external tools, data sources, and APIs. You can now augment the list of built-in tools with any MCP server that supports the stdio transport layer. MCP servers can be managed within the Q Developer user interface, making it easy to add or remove servers, and modify tool permissions. By extending your IDE, Q Developer is able to provide more customized responses by orchestrating tasks across native and MCP server-based tools.
MCP support is available within the Visual Studio Code and JetBrains IDE plugins, and Amazon Q Developer CLI. To get started, visit the Amazon Q Developer documentation or read the blog to learn more.
