Salesforce Enhances MuleSoft Agent Fabric with Seamless Automated Discovery

Salesforce is making enhancements to MuleSoft Agent Fabric to bridge and simplify the fragmented landscape into a governed and cohesive agent network, giving you a single control plane for all your AI agents, tools, and metadata.

This update centers around new Agent Scanners, giving you the ability to automatically detect and catalog 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 is delivering a trusted, open, and interoperable platform, empowering organizations to deploy the full potential of their Agentic Enterprise.

“The most successful organizations of the next decade will be those that harness the full diversity of the multi-cloud AI landscape. The expanded capabilities of MuleSoft Agent Fabric give you the freedom to innovate across any platform while maintaining the unified visibility and control needed to scale,” said Andrew Comstock, SVP and GM, MuleSoft, Salesforce.

Starting with Agent Scanners, users can go beyond manual discovery and get 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. You can simply link different environments, such as 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’re designed to do.

Deep Metadata Extraction: Agent Scanners go beyond the surface of an agent and automatically extract its specific capabilities (e.g., querying a database or processing a refund), the large language models (LLMs) powering it, and the data it has permission to access where available. They then normalize 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 catalog 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 cataloging agents that ensures your 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, plus a curated list of public MCP servers from the Official MCP Registry.

Bringing all agents and tools together enables users to optimize and control them with ease. MuleSoft Agent Visualizer gives you a view of your entire AI footprint and provides advanced filtering and search capabilities.

MuleSoft Agent Fabric replaces the burden of manual oversight with automated visibility, allowing every team to eliminate operational silos and helping to ensure that every agent is an accountable and productive part of the Agentic Enterprise.

Here is how its new capabilities can work within day-to-day operations:

Gain oversight without the legwork: For security and compliance officers in banking managing multi-cloud AI deployments, the technical heavy lifting is done for you. When a new loan-processing agent pops up in Amazon Bedrock, an Agent Scanner surfaces it in a unified view automatically. You can immediately see which LLMs are powering it and exactly which financial databases it’s authorized to access. We standardize the data from every provider into A2A format, so verifying a third-party agent is just as easy as verifying a native one.

Connect siloed Innovations: Data scientists in logistics are often building powerful internal tools, such as MCP servers for proprietary databases. Instead of those tools staying hidden, your team can now bring them into the fold by simply pasting a URL into the registry. This makes your custom logistics or optimization data discoverable and reusable for the rest of the company—while keeping it firmly under your security policies.

Optimize AI spend: Use MuleSoft Agent Visualizer to filter your entire landscape by job type. If you notice three different regional teams are all paying for separate summarization agents on different AI platforms, you can consolidate them into one high-performing asset. It’s the easiest way to cut redundant costs and reallocate your budget toward real innovation.

Agent Scanners for major cloud environments, including Salesforce Agentforce, Amazon Bedrock, Google Cloud’s Vertex AI, and Microsoft Copilot Studio, are generally available in January 2026.

A curated set of third-party MCP servers in MuleSoft Agent Registry is also generally available in January 2026.

The ability to add MCP servers via URL to MuleSoft Agent Registry is generally available in January 2026, with the ability to add bespoke agents via URL coming in Q1 FY 2027.

Enhanced search for agents and MCP servers in MuleSoft Agent Visualizer is generally available in January 2026.

For more information about this news, visit www.salesforce.com.