Docs
Connector Overview

MuleSoft AI Chain (MAC) Connector Overview

The MuleSoft AI Chain (MAC) project brings the power of LangChain4j (opens in a new tab) to the MuleSoft ecosystem, enabling seamless integration of AI capabilities. The project, inspired by Dmytro Liubarskyi (opens in a new tab) and Lize Raes (opens in a new tab), offers a robust, open-source framework dedicated to the MuleSoft community.

What is the MuleSoft AI Chain (MAC) Connector?

The MuleSoft AI Chain Connector is designed to help developers easily build and manage AI-driven agents within the MuleSoft Anypoint Platform. It provides the tools and support needed to integrate Large Language Models (LLMs), embeddings, and other advanced AI services into MuleSoft applications.

Connector Overview

Key Features

The MuleSoft AI Chain Connector simplifies AI integration into MuleSoft applications with:

  • Seamless Interaction with LLMs: Effortlessly integrate and utilize large language models (LLMs) for tasks such as natural language processing, text generation, and more, including advanced features like text generation, analysis, and complex language tasks.
  • Embeddings and Search: Leverage embeddings to handle tasks like text similarity, document search, and clustering, all within MuleSoft applications.
  • Optimized Performance: Designed for high efficiency and performance in enterprise-grade MuleSoft applications, ensuring smooth handling of AI operations.
  • File-Based Local Vector Stores: Create simple, file-based vector stores directly within the connector, ideal for local use or POC designs. For external vector store integration, use the dedicated Vector Store Connector.
  • Comprehensive AI Tools and Services: Access a wide array of AI-driven features, including Retrieval-Augmented Generation (RAG) for document retrieval, dynamic tool integration (Function Calling), and image model support for tasks like recognition and manipulation.

Integration with MuleSoft Ecosystem

The MuleSoft AI Chain Connector integrates tightly with the MuleSoft ecosystem, offering:

  • Customizable Tooling: Use configuration files for flexible setups tailored to your needs.
  • Easy Tooling Management: Access and manage a wide range of AI tools directly through Anypoint Exchange.

Enhanced Capabilities using Anypoint Platform

By leveraging MuleSoft’s powerful platform, the MAC Connector enhances AI projects with:

  • AI Lifecycle Management: Manage the entire lifecycle of AI agents, from design to deployment, using MuleSoft's Anypoint Platform.
  • Centralized AI Design: Design agents using the Anypoint Design Center for seamless workflow integration.
  • Comprehensive Monitoring: Track and monitor your AI agents with Anypoint Monitoring and visualization tools.
  • Low-Code Development: Build AI applications with minimal code using Anypoint Studio and Anypoint Code Builder.
  • Built-In Testing: Ensure reliability with a robust unit-testing framework using MUnit in Anypoint Studio.

Supported LLM Provider

The MuleSoft AI Chain Connector supports the following LLM Providers:

  • Anthropic
  • Azure OpenAI
  • Mistral AI
  • OpenAI
  • Google Gemini
  • Hugging Face
  • Ollama
  • GroqAI

Table of Supported Operations by LLM Provider

Not all the operations are supported by each embedding store, following a detailed view.


NameAnthropicAzure OpenAIGemini AIMistral AIOpenAIHugging FaceOllamaGroq AI
Chat answer prompt
Chat answer prompt with memory
Agent define prompt template
Embedding new store
Embedding add document to store
Embedding add folder to store
Embedding query from store
Embedding get info from store
RAG load document
Sentiment analyze
Tools use AI Service---
Tools use AI Native
Toxicity detection------
Image read-------
Image read scanned documents-----
Image generate-------

-* depends on the model used

Additional Integrations

MuleSoft AI Chain Connector integrates seamlessly with other MAC Projects AI Connectors and the MuleSoft ecosystem, offering enhanced functionalities.