New MuleSoft Innovations from Salesforce Enable Secure, Scalable AI Agent Orchestration for Agentic Transformation

MuleSoft Model Context Protocol (MCP) Support transforms any application or API into tools and resources for AI agents in a few clicks

MuleSoft Agent2Agent (A2A) Support enables agents to communicate, collaborate, and take coordinated actions across the enterprise with governance

New generative AI tools in MuleSoft’s Integrated Developer Environment (IDE) allow developers to build integrations faster and accelerate project development

Salesforce today announced new MuleSoft AI capabilities that enable organizations to build a foundation for secure, scalable AI agent orchestration. These capabilities deliver essential support for AI agent protocols, like Model Context Protocol (MCP) and Agent2Agent (A2A), by allowing customers to make any existing integration, API, and application accessible and understandable by AI agents and build multi-agent workflows with robust governance. And, with new generative AI development tools for increased developer productivity, MuleSoft is helping organizations accelerate their transformation into agent-driven enterprises. 

With the recent launch of Salesforce Agentforce 3, which includes native MCP support, customers can also use MuleSoft’s new features to turn APIs into MCP servers and extend Agentforce with new opportunities for agent interoperability without compromising control.

For example, the new MuleSoft capabilities allow organizations to automate IT issue resolution to enhance customer experiences while enabling IT teams to focus on more strategic, high-value work. Customers can build an observability agent that detects a critical server error in an observability and security platform like Datadog (agent-to-system) and alerts the specialized database triage agent (agent-to-agent). They can also expand the workflow to enable the triage agent to then query a knowledge base for the error signature, identify the fix, and instruct a remediation agent to restart the appropriate cloud service and post a status update to Slack (agent-to-agent to agent-to-system).

As modern businesses adopt more AI agents and the number of applications and AI models they use multiplies, their technology infrastructure becomes increasingly complex and siloed. In fact, integration is one of the biggest barriers between AI’s promise and enterprise reality, with 95% of IT leaders citing it as the top hurdle to making AI effective. The existing enterprise architecture is built for running applications, but it’s not equipped to manage thousands — or tens of thousands — of agents across the enterprise. This radical shift introduces an entirely new class of challenges around orchestration, integration, and governance. 

MuleSoft has long been a leader in helping organizations digitally transform for the AI era, empowering them with tools for integration, APIs, and automation. Now, as agents become central to an organization’s competitive advantage, MuleSoft’s agent orchestration capabilities provide organizations with new tools for agentic transformation.

MuleSoft’s new AI and agent-focused capabilities are critical in preparing customers for the autonomous enterprise.

New agent orchestration capabilities include: 

MCP support

MCP is rapidly gaining momentum as a standardized, open-source framework for enabling seamless and secure bidirectional communication between LLMs or AI agents and diverse external systems like Salesforce. 

MuleSoft MCP Support enables integrations with LLMs and enterprise systems with just a few clicks and provides agents with the ability to take action in any system with governance. 

• MuleSoft MCP Connector — Transform any application or API into an agent-ready asset by bringing MCP to every API
• MuleSoft for Agentforce: Topic Center — Turn APIs into intelligent actions to empower agents, whether for Agentforce or any other AI agent platform 
• MuleSoft Flex Gateway: MCP Support — Secure and standardize communication with AI agents and models through a unified platform

A2A support

The A2A protocol is also growing in popularity as an essential standard for enabling secure, scalable, and discoverable communication among multiple AI agents. A2A focuses on direct agent-to-agent collaboration, addressing the critical need for a common language between diverse AI models.

MuleSoft A2A Support enables secure A2A communication and discoverability across the agentic enterprise.

• MuleSoft A2A Connector — Create seamless communication across any agent by exposing them as an A2A server or client
• MuleSoft Flex Gateway: A2A support — Use a unified gateway to allow agents to find each other to accomplish multi-step tasks quickly

New generative AI tools

New generative AI tools built into Anypoint Code Builder, MuleSoft’s Integrated Developer Environment (IDE), let developers increase productivity by building APIs and integrations faster with natural language prompts and take those capabilities to any AI-first IDE. 

• Anypoint Code Builder: AI IDE support — Extend MuleSoft development capabilities to any MCP-supported IDE, such as Cursor or Windsurf
• Einstein for Anypoint Code Builder: API spec — Accelerate development by automatically aligning your work with established format and syntax using natural language to generate API Specifications
• Einstein for Anypoint Code Builder: Dataweave — Ramp up faster and quickly learn MuleSoft’s proprietary technology with generative Dataweave Transformations via natural language
• Anypoint Exchange: AI-generated documentation — Auto-generate standardized API documentation at the time of publication to make it easier for consumers to understand how the API functions

“MuleSoft’s agent orchestration marks the next evolution in enterprise integration. It’s how organizations will power truly intelligent, actionable interactions by unifying APIs, agent actions, governance, and multi-agent coordination.” – Andrew Comstock, SVP and GM of MuleSoft, Salesforce.

“MuleSoft has enabled us to build a composable architecture and data foundation needed to scale AI across AstraZeneca — from HR to R&D to Commercial. Their commitment to evolving industry protocols and the crucial semantic layer ensures secure and scalable orchestration of agent-to-agent and agent-to-system actions, making our strategic partnership with Salesforce and MuleSoft vital for our ambitious AI journey.” – Wayne Filin-Matthews, Chief Distinguished Architect, AstraZeneca

“We’re transforming our client experience by creating a multi-agent AI journey designed to proactively deliver personalized interactions. Our composable foundation, powered by MuleSoft, is key to this. It seamlessly integrates our data, allowing our AI agents to access crucial information and rapidly unlock advisor and client value.” – Greg Beltzer, Head of Digital, U.S., EMEA, and APAC, RBC Wealth Management