--- schema_version: "1" id: 6f094cdfbcc1a221a3b81a64a82bda911bf2695768c870726cc85f88c18f54b3 title: Amazon Bedrock Connector 1.1 collection: mulesoft version: current locale: en-us portal_url: https://docs.salesforce.com/mulesoft/current/en-us/amazon-bedrock-connector/latest/index.md canonical_url: https://docs.mulesoft.com/amazon-bedrock-connector/latest/ source_site: docs.mulesoft.com content_type: documentation content_hash: e67f845b941c1bf13bc671b37e80cf970777091c8d26ea34d62f9bc8156d5c49 description: MuleSoft Documentation Site release: "1.1" latest: true --- --- product: Amazon Bedrock Connector version: 1.1 is-latest-version: true --- # Amazon Bedrock Connector 1.1 > For the full documentation index, see: https://docs.mulesoft.com/llms.txt Anypoint Connector for Amazon Bedrock (Amazon Bedrock Connector) provides access to Amazon Bedrock, a fully managed service offering high-performing foundation models (FMs) and agentic AI capabilities. The connector enables customers to invoke Bedrock models, analyze PDFs and images through multimodal interactions, and integrate agents running on Amazon Bedrock AgentCore, including runtime and memory capabilities, directly within Mule flows. The connector supports use cases such as prompt-based inference, Retrieval-Augmented Generation (RAG), document and image analysis, and stateful, agent-driven workflows over enterprise data. By abstracting model and API-specific complexity, the connector provides a unified, consistent interface for integrating Amazon Bedrock capabilities across MuleSoft applications and workflows. For information about compatibility and fixed issues, see the Amazon Bedrock Connector release notes. ## Before You Begin To use this connector, you must be familiar with: - Anypoint Connectors - Mule runtime engine (Mule) - Elements and global elements in a Mule flow - How to create a Mule app using Anypoint Code Builder or Anypoint Studio - Amazon Web Services (AWS) and Amazon Bedrock Before creating an app, you must have: - Java 17 (required for compilation and runtime) - Apache Maven - An AWS account with access to Amazon Bedrock - Valid AWS credentials - Anypoint Platform - The latest versions of Anypoint Code Builder or Anypoint Studio ## Amazon Bedrock Connector Product Spotlight Video Watch the Amazon Bedrock Connector Product Spotlight video to see a quick overview of Amazon Bedrock Connector. ![](https://play.vidyard.com/ydFAiLCrZwrJyjWf2uoa2M.jpg) ## Supported Foundation Model Providers Amazon Bedrock Connector provides access to all foundation models supported by Amazon Bedrock, including models from Amazon and third-party AI providers, through a single, unified MuleSoft interface. Custom models aren’t supported. - AI21 Labs J2 - Amazon Nova - Amazon Titan - Anthropic Claude - Cohere - Meta Llama 2 - Meta Llama 3 - Mistral AI - Stability AI ## Key Features Amazon Bedrock Connector simplifies the integration of generative and agentic AI capabilities into Mule applications with: - **Seamless Interaction with Foundation Models and AgentCore Agents** Invoke leading foundation models and integrate agents running on Amazon Bedrock AgentCore directly within Mule flows. Use AgentCore runtime and memory capabilities to build contextual, multi-step agentic workflows across enterprise systems. - **Multimodal AI with File and Image Attachments** Send PDFs and images alongside prompts to supported multimodal models to analyze documents, images, charts, and other visual content and use the results in downstream Mule workflows. - **Optimized Performance in Mule Apps** Build enterprise-grade AI applications without managing model infrastructure. Amazon Bedrock’s managed capabilities combined with MuleSoft integration enable you to securely operationalize AI across applications and workflows. - **Unified Access to Bedrock Models** Access supported foundation models through a consistent MuleSoft interface. This reduces model-specific integration complexity and makes it easier to use different models across your AI applications. ## Connector Capabilities Amazon Bedrock Connector provides capabilities for building generative, multimodal, and agentic AI experiences in Mule applications: - **Foundation Models** Access supported Amazon Bedrock foundation models to generate content, analyze information, perform reasoning, and build AI-powered experiences. - **Multimodal AI** Include PDFs and images with prompts to analyze documents, charts, diagrams, and visual content using supported multimodal models. - **Amazon Bedrock AgentCore** Integrate agents running on Amazon Bedrock AgentCore into Mule workflows. Invoke agents and use memory capabilities to build contextual, stateful agent experiences across enterprise systems. - **Embeddings** Generate vector embeddings to enable semantic search, similarity matching, and Retrieval-Augmented Generation (RAG) use cases. - **Tools Integration** Connect AI experiences with APIs, applications, and enterprise data to enable actions and multi-step business workflows. - **Image Generation** Use supported image models to generate images directly within Mule workflows. - **Streaming** Stream model and agent outputs incrementally as they are generated. This enables responsive, real-time AI experiences without waiting for the complete response. ## Amazon Bedrock Service Features Amazon Bedrock provides capabilities for building secure, grounded, and agentic generative AI applications: - **Knowledge Bases** Ground foundation models and agents in your organization’s private data using Retrieval-Augmented Generation (RAG) to deliver more relevant, accurate, and contextual responses. - **Agents and AgentCore** Build agents that execute multi-step tasks across enterprise systems and data sources. Amazon Bedrock AgentCore provides capabilities for deploying and operating agents, including runtime, memory, identity, and other services for production agentic applications. - **Memory** Maintain context across agent interactions to deliver more personalized and continuous experiences. Memory enables agents to retain relevant information and use historical context in future interactions. - **Guardrails** Apply configurable safeguards based on your application requirements and responsible AI policies to evaluate model inputs and responses. - **Security and Privacy** Protect generative AI workloads using AWS security, identity, and encryption capabilities. Maintain control over your data and use AWS services such as AWS Identity and Access Management (IAM) and AWS Key Management Service (AWS KMS) to manage access and encryption. ## Enhanced Capabilities via Anypoint Platform You can leverage Anypoint Platform to provide enhanced capabilities, including: - **End-to-End Lifecycle Management for AI Agents** Manages the complete lifecycle of AI agents, from design to deployment. - **Centralized AI Agent Design** Streamlines design through Anypoint Design Center. - **AI Agent Portal** Provides centralized management and access via Exchange and Anypoint Experience Hub. - **Comprehensive Monitoring** Enables detailed monitoring and visualization with Anypoint Monitoring and Visualizer. - **Low-Code Development Environment** Simplifies development with Anypoint Studio and Anypoint Code Builder. - **Robust Unit-Testing Framework** Ensures thorough testing capabilities with MUnit, available in Anypoint Studio. ## Additional Integrations Amazon Bedrock integrates seamlessly with the MuleSoft ecosystem: - **Dynamic Tooling through Configuration Files** Allows for flexible and customizable setups. - **Extensive Tooling through Anypoint Exchange** Facilitates easy integration and management of various tools. ## Next Step After you complete the prerequisites, you are ready to create an app and configure the connector using [Anypoint Studio](https://docs.mulesoft.com/amazon-bedrock-connector/latest/amazon-bedrock-connector-studio) or [Anypoint Code Builder](https://docs.mulesoft.com/amazon-bedrock-connector/latest/amazon-bedrock-connector-config-acb). ## See Also - [Introduction to Anypoint Connectors](https://docs.mulesoft.com/connectors/introduction/introduction-to-anypoint-connectors) - [Amazon Bedrock Connector Reference](https://docs.mulesoft.com/amazon-bedrock-connector/latest/amazon-bedrock-connector-reference) - [Salesforce Help](https://help.salesforce.com)