Salesforce expands MuleSoft Agent Fabric with automated discovery for any AI agent or tool

Salesforce has announced major enhancements to its MuleSoft Agent Fabric solution. Salesforce says MuleSoft Agent Fabric, bridge and simplify this fragmented landscape into a governed and cohesive agent network. It give businesses a single control plane for all their AI agents, tools, and metadata.

This update centres around new Agent Scanners, giving you the ability to automatically detect and catalogue AI agents across Salesforce Agentforce, Amazon Bedrock, Google Cloud’s Vertex AI, and other agent platforms. For other assets, like Model Context Protocol (MCP) servers and bespoke agents, additional capabilities make registration just as simple.

By streamlining the integration of any agent or MCP server, regardless of vendor, Salesforce says it is delivering a trusted, open, and interoperable platform. Enabling organisations to deploy the full potential of their Agentic Enterprise.

For example, an AI engineer won’t have to work alone to audit and scour cloud environments for agents built across inventory, logistics, and customer service teams. Instead, Agent Scanners can automatically find an inventory forecasting agent in Google Cloud’s Vertex AI and register it alongside a customer support agent built in Agentforce, for governance and management — no manual data entry, no visibility gaps, and no surprises.

“The most successful organisations of the next decade will be those harnessing the full diversity of the multicloud AI landscape.

“The expanded capabilities of MuleSoft Agent Fabric give you the freedom to innovate across any platform. At the same time maintaining the unified visibility and control needed to scale,” says Andrew Comstock, SVP & GM, MuleSoft, Salesforce.

A Single Source of Truth for AI Agents and tools

Starting with Agent Scanners, organisations can go beyond manual discovery. The solution provides the visibility and technical context required to trust agents deployed across your enterprise:

• Continuous Multi-Ecosystem Agent Discovery. Instead of tracking down agents across platforms yourself, Agent Scanners do the legwork for the business. Managers can simply link different environments, like Salesforce Agentforce, Amazon Bedrock, and Google Cloud’s Vertex AI, and the scanners start identifying running agents in minutes.They constantly patrol these ecosystems to spot new or updated agents. Identify their endpoints, and understand what they are designed to do.
• Deep Metadata Extraction: It’s not enough to know that an agent exists; managers need to know what it’s able to access and action. Agent Scanners go beyond the surface of an agent and automatically extract its specific capabilities. (e.g., querying a database or processing a refund).Investigating the large language models (LLMs) powering it, and the data it has permission to access where available. They then normalise and map the metadata to Google Cloud’s standard agent-to-agent (A2A) protocol card specifications.
• Seamless Cataloging: The days of stale spreadsheets are over. Everything that Agent Scanners find is continuously synced to MuleSoft Agent Registry. A central catalogue where agents, MCP servers, and AI tools can be registered and made discoverable by developers or other agents.It’s an always-on approach to cataloguing agents ensures security teams are always looking at real-time data. Not a snapshot from three months ago.
• It’s not just AI agents on major platforms that can be automatically discovered. To help ensure no AI asset is left behind, MuleSoft Agent Fabric also includes flexible registration for homegrown agents and MCP servers via URL. In addition to a curated list of public MCP servers from the Official MCP Registry.

Enterprise Times: What this means for businesses

The Agentic Enterprise era has arrived, with business leaders and their teams adopting AI agents at an unprecedented pace. IDC forecasts that the number of actively deployed AI agents will surpass 1 billion globally by 2029, representing a forty fold increase over 2025. Research by Software AG last year showed that 50% of employees use non-company issued AI tools.

This study surveyed 6,000 knowledge workers. Currently, 75% of knowledge workers use AI, with this expected to reach 90% soon. Interestingly, Over half use personal AI tools, and many would keep using them even if banned by their employer. This rapid proliferation presents a significant challenge: agent sprawl.

Specialised AI agents and tools are being implemented across various teams, functions, and platforms—often lacking sufficient visibility and governance. This situation raises concerns regarding shadow AI.

Without a scalable solution to locate and monitor agents operating across multiple platforms, organisations face difficulties in understanding not only which agents are active, but also how these agents make decisions, what actions they perform, and the outcomes they deliver. Bringing all organisation’s agents and tools together is vital.

It enables the business to optimise and control the use and future development of AI with more ease. Tools such as MuleSoft gives enterprises the necessary view of their entire AI footprint.

The post Salesforce expands MuleSoft Agent Fabric with automated discovery for any AI agent or tool appeared first on Enterprise Times.