Building Agent Networks for Agent Fabric
Agent Fabric manages and coordinates the execution of agents across your enterprise, regardless of where they’re deployed. Agent Fabric solves the problem of integrating and automating complex processes that involve multiple agents and tools.
Complex tasks often require a series of steps, with each step handled by a different agent or tool. Managing this process manually is difficult and error-prone. Agent networks (networks of agents in a domain) act as central hubs for defining, validating, and executing these multi-step processes.
Define your agent network in a simple, human-readable YAML file in Anypoint Code Builder desktop. This approach abstracts away the underlying technical complexities and so that you focus on the business constraints and context of your process without needing to understand the inner workings of the orchestration engine.
Don’t worry, we give you a head start by providing you with a YAML template in your agent network project. MuleSoft Dev Agent can help you configure it for your business environment, publish agent network assets to Anypoint Exchange, and deploy your agent network instance.
For more information about Agent Fabric, see Agent Fabric Overview.
Agent Network Components
Brokers, agents, and Model Context Protocol (MCP) servers are supported in an agent network. A broker is an intelligent routing service that coordinates task delegation across specialized agents in your enterprise. A broker is defined by the agents and MCP servers it can leverage to accomplish tasks.
A broker is a specialized agent that is shown in Anypoint Exchange after you publish your agent network assets and can be reused by other brokers.
Agents and MCP servers are defined locally in the agent network, or externally. Externally-defined agents and MCP servers are defined in a different agent network or elsewhere in your company. Your agent network can use both locally-defined and externally-defined components to complete tasks across your enterprise.
Considerations
Agent networks have these considerations.
-
An agent network project supports only one domain (one YAML file per project). For multiple domains, create a separate project for each.
-
These authentication types are supported.
-
Basic
-
Client Credentials
-
Anypoint Client Credentials
-
-
A2A specification 0.3.0 is supported. Brokers use the A2A protocol to accept requests to reach other agents.
-
These A2A features aren’t available.
-
Task History
-
Push Notifications Config
-
Streaming
-
-
Text-based prompts and responses are supported. Image and binary message/artifact types aren’t supported.
-
All LLM models in your agent network project must support structured responses in JSON format. For example, a
gpt4.1
model is supported; agpt4
model isn’t. -
These LLMs are supported.
-
Azure OpenAI
-
OpenAI Direct API
-
-
When you add governance policies to your agent network project YAML file, those policies persist between deployments. However, if you add governance policies at run-time, those policies don’t persist. The next time you deploy your agent network, the governance policies used are the ones in the
agent-network.yaml
file. -
These deployment targets are supported.
-
CloudHub 2.0
-
Runtime Fabric (limited availability)
-