Salesforce Launches MuleSoft Agent Fabric to Orchestrate and Govern Any AI Agent Across the Agentic Enterprise

MuleSoft Agent Fabric is a new solution to discover, orchestrate, govern, and observe any AI agent, regardless of where it's built or operating

Customers like Barco, r.Potential, Rush University System for Health, and Wynn and Encore Las Vegas are using MuleSoft Agent Fabric to securely and confidently manage agents across their businesses

As companies accelerate their adoption of AI, they're facing an explosion of agents across teams, platforms, and vendors. While this surge holds massive potential, it also introduces a new form of fragmentation - agent sprawl - where disconnected workflows, redundant automations, and compliance blind spots emerge. Without the right foundation, unmanaged agents risk creating chaos instead of driving productivity, making it harder to govern data, enforce security, and deliver consistent customer and employee experiences at scale.

That's why Salesforce today announced MuleSoft Agent Fabric, a new solution that transforms unmanaged AI agents into a secure and intelligent network. MuleSoft Agent Fabric provides a single place to register, orchestrate, govern, and observe every agent, regardless of where it was built. Much like an air traffic controller ensures planes from different airlines take off, land, and share airspace safely, MuleSoft Agent Fabric acts as the backbone that connects and coordinates an enterprise's disparate digital workforce, turning chaos into cohesion and transforming fragmented agents into a trusted, high-performing network.

Imagine a global retailer with one agent tracking inventory, another updating prices, and a third detecting fraud. MuleSoft Agent Fabric helps to ensure these agents don't operate in silos but rather work together. So whenever stock runs low, pricing adjusts automatically and fraud checks happen in real time, all while governance keeps sensitive data secure.

Why it matters

AI agent adoption is projected to surge by 327% in the next two years, with 40% of enterprise applications expected to include agents within a year. Each embedded agent promises to streamline tasks within its own application, but they are blind to the broader enterprise - unable to orchestrate actions across domains and lacking the necessary guardrails for secure, cross-system collaboration.

MuleSoft Agent Fabric delivers the missing foundation - governing, orchestrating, and monitoring agents across ecosystems, so they can work together securely, intelligently, and at scale. This empowers organizations to confidently accelerate their journey to becoming Agentic Enterprises, where humans and AI agents work side by side, with the clarity and control needed to facilitate security and compliance.

MuleSoft is uniquely positioned to tackle this challenge. For over a decade, enterprises have trusted MuleSoft to connect applications, data, and processes across every system. That same heritage in integration and governance now extends to AI agents, so they can interoperate securely across any ecosystem, just as MuleSoft has done for APIs and applications worldwide.

How it works

MuleSoft Agent Fabric helps customers orchestrate and govern their diverse ecosystem of agents with four capabilities that work together to power the Agentic Enterprise:

• Discover Any Agent or Tool: MuleSoft Agent Registry is the central catalog where every AI agent or tool - including MCP and A2A servers - can be registered and made discoverable by developers or other agents. This makes every AI asset easy to find, reuse, and compose into workflows, helping enterprises avoid duplication and accelerate delivery.
• Orchestrate Agents Across Ecosystems: MuleSoft Agent Broker is an intelligent routing service that organizes AI agents and tools into business-focused domains and dynamically routes tasks across them.Powered by your LLM of choice and connected through A2A and MCP, the Broker enables even the most complex, multi-step processes to execute seamlessly across diverse agents and systems.
• Enforce Trust and Security at Every Agent Interaction: MuleSoft Agent Governance provides enterprise-grade guardrails that apply security, compliance, and policy controls to every agent interaction. This allows organizations to scale AI adoption safely, helping to ensure every action is consistent, secure, and aligned with enterprise and regulatory requirements.
• Gain End-to-End Visibility into Agent Decisions: MuleSoft Agent Visualizer gives IT teams a dynamic map of their agent ecosystem, showing how agents connect, interact, and perform. By turning black-box AI into transparent, observable systems, it provides the insights needed to optimize performance, prevent failures, and build trust in the agentic workforce.

With Salesforce's Agentforce customers get a complete platform out of the box for building and deploying autonomous AI agents. MuleSoft Agent Fabric extends Agentforce to orchestrate with other third-party agents that don't interact through Agentforce.

Go deeper

By providing a single place to orchestrate and govern agents - including those built on but not limited to platforms like Agentforce - MuleSoft Agent Fabric enables AI to solve complex, multi-step business problems across diverse industries:

• Mortgage Application Automation: MuleSoftAgent Fabric can be used to securely orchestrate the various components of the mortgage application process.

  For example, a "Mortgage Assistant" agent - powered by Agentforce and embedded in a banking platform - uses the MuleSoft Agent Broker to intelligently route a single customer inquiry across siloed SaaS and homegrown agents. Agentforce captures the customer's information, and coordinates with an external Credit Check Agent for real-time credit checks, a DocuSign IAM Agent for secure document signatures, and a homegrown Compliance Agent to enforce regulatory policies. The MuleSoftAgent Registry makes each of these specialized agents easily discoverable for Agentforce, while MuleSoft Agent Governancehelps to ensure every external agent interaction - from data access to policy checks - is secure and auditable. This coordinated workflow prevents critical handoffs from failing, reducing delays, errors, and significant compliance risks.

• Real-Time Supply Chain Logistics: MuleSoft Agent Fabric can be used to connect disparate systems to create a responsive, intelligent supply chain.

  For example, an "Operations Agent" receives a prompt about a potential shipment delay. It uses the MuleSoft Agent Broker to coordinate with a logistics partner's "Fleet Agent" to re-route a delivery, while an "SAP Agent" updates inventory in real time. A separate "Quality Control Agent" then flags any potential issues at the warehouse. The MuleSoft Agent Visualizer provides IT teams with a clear, interactive view of this complex agent activity, helping them to proactively surface errors and optimize performance. This helps to ensure every insight or decision from an agent triggers the right follow-through across systems.

• Partner and Employee Onboarding: MuleSoft Agent Fabric can be used to manage a complex onboarding process for partners.

  For example, a "Partner Portal Agent" uses theMuleSoft Agent Broker to coordinate with multiple backend systems. It intelligently routes requests to a "Sales Agent" to assign a new partner ID, to a homegrown "IT Agent" for systems access, and to a "Knowledge Agent" to surface relevant articles and training. With MuleSoft Agent Governance, the IT team can control agent permissions and data access to help ensure the new partner can only see what's needed for their onboarding, all while maintaining control of company data.

Perspectives

• "The reality is, most enterprises live in a multi-vendor world, and that won't change with AI. Just as companies rely on countless applications across different ecosystems, they'll soon have AI agents from every SaaS provider and every major LLM. The strategic challenge isn't building a single agent, but enabling all of them to work together. MuleSoft Agent Fabric gives every organization the ability to govern and orchestrate all their agents in a cohesive and trusted way." - Andrew Comstock, SVP and GM of MuleSoft, Salesforce
• "MuleSoft Agent Fabric gives us the foundation to orchestrate thousands of agents at scale, securely and in real time. It's more than coordination - it's the connective tissue for the next generation of enterprise intelligence. By unifying disparate agents into one secure fabric, we help customers evolve from isolated automations to a fully orchestrated, adaptive ecosystem." - Greg Shewmaker, CEO, r.Potential
• "As AI agents become critical in processes that drive our day-to-day business operations, governance and transparency are non-negotiable. MuleSoft Agent Fabric provides the guardrails we need to adopt AI responsibly and securely, without slowing down innovation." - Joris Diependaele, Head of Integration and AI, Barco
• "MuleSoft Agent Fabric is a strong fit to meet all our compliance and data security requirements across the highly regulated areas of our business and across multiple geographic locations. We can retain control over the infrastructure and also leverage our existing ecosystem to build our agentic future. This hybrid approach gives us the flexibility in solutioning across the organization" - Karthik Palani, Sr Mgr - Eng & Integrations, Wynn and Encore Las Vegas
• "The future of work is agentic. MuleSoft Agent Fabric lays the foundation for that future by transforming disconnected agents into a cohesive, governed, and high-performing digital workforce." - Shivani Marrero, Senior MuleSoft Developer, Rush University System for Health

MuleSoft Agent Fabric gives us the foundation to orchestrate thousands of agents at scale, securely and in real time.

Availability

• Agent Registry: Will be generally available starting October 2025.
• Agent Broker: Beta available now, will be generally available starting October 2025.
• Agent Governance (Flex Gateway for MCP & A2A): Available now.
• Agent Visualizer: Will be generally available starting October 2025.

Learn more

This article may include references to services or features that are still in development and are unreleased. Customers should make their purchase decision based on fully released and available features.