Contact Us 1-800-596-4880

Overview of Agent Networks

An agent network is a coordinated group of agents, brokers, LLMs, and MCP servers that acts as a central hub for defining, validating, and executing agentic processes across your enterprise.

An agent network provides the building blocks of your agentic deployment while MuleSoft Agent Fabric helps you maximize the potential of every AI agent with centralized discovery, orchestration across agents and tools, cross-ecosystem governance, and full transparency into agentic interactions.

This page provides foundational concepts about agent networks. For version-specific implementation guidance, see:

Key Benefits of Agent Networks

Create robust, automated agent networks with these key benefits.

  • Simplified Development

    Define your agent processes in an intentional way using a simple YAML file, which is easier and faster than writing complex code.

  • Safety and Governance

    Ensure control and compliance across every agent and tool interaction with enterprise-grade governance.

  • Observability

    Gain insight into agent actions with a visual trace of their decision-making.

  • Flexibility

    Coordinate any type of agent and tool, regardless of where it’s built and deployed so you can build a diverse network of agents.

  • Tool and Agent Invocation

    Manage the invocation of both deterministic (tool-based) and probabilistic (LLM-based) actions.

The Guided Determinism Pattern

Brokers in agent network 2.0 architecture use a guided deterministic approach by separating steps requiring probabilistic LLM reasoning from those requiring deterministic control-flow logic.

  • Probabilistic (LLM-based) nodes handle complex, open-ended decisions that require nuanced judgment, such as classification or AI-powered thinking.

  • Deterministic nodes manage all remaining predefined execution paths, ensuring a fixed and guaranteed workflow after a key probabilistic judgment has been finalized.

This structure allows brokers to apply high-level LLM intelligence where complex judgment is needed, while the overall agent graph maintains reliable, rule-based predictability across the operational flow.

Agent Network Components

Agent networks use LLMs for reasoning and planning and integrate with Anypoint Connector for MCP (Model Context Protocol) and Anypoint Connector for Agent2Agent (A2A) communication.

You define a broker and its nodes in Agent Script. Nodes connect in a graph so each path runs in a specific order and can combine deterministic steps with LLM reasoning. After you publish the agent network, brokers appear as specialized agents in Anypoint Exchange, and other brokers can reuse them. Agents and MCP servers can be defined in this project or referenced from another agent network or elsewhere in your company. Agent assets must be A2A-compliant.

For definitions of these components, see Agent Fabric Glossary.

Agent Network YAML and Agent Script

An agent network project defines a structured configuration for multi-agent systems, enabling orchestration of AI agents with external services, tools, and inter-agent communication. This format provides a declarative way to define agent capabilities, dependencies, and service integrations.

An agent network project includes these files:

/my-agent-network-project
  - exchange.json
  - agent-network.yaml
  /brokers
    - broker1.agent
  • exchange.json: Contains asset metadata available in Anypoint Exchange after publishing your agent network assets.

  • agent-network.yaml: Contains a registry section that defines Exchange assets used in your project and a context section that defines connections and policies for the project.

  • .agent files: Contain broker and node definitions and configurations that enable multi-agent orchestration in your project.

For more information, see Agent Network 2.0 Project File Reference.

For a complete, working example you can use as a starting point for your own agent network project, see Example: Building an IT Investigation Broker. The example walks through a fully configured agent-network.yaml, exchange.json, and /brokers directory that you can adapt to your own project.

Agent Network Architecture

This diagram shows an agent network deployed to a shared space in CloudHub 2.0 using a single Omni Gateway for ingress and egress. The network includes agents and MCP servers and is observed in Anypoint Monitoring.

an agent network deployed to a shared space in CloudHub 2 using a single Omni Gateway for ingress and egress. The network includes agents and MCP servers and is observed in Anypoint Monitoring
1 Publish the agentic assets to Anypoint Exchange for discovery and reuse after you define the agent network (brokers, agents, MCP servers) in the agent network YAML in Anypoint Code Builder.
2 Deploy the agentic assets to CloudHub 2.0 (managed in Runtime Manager).
3 Enforce policies, manage connections, and emit telemetry through a single Omni Gateway that handles both ingress to brokers/API endpoints and egress to external agents and services.
In a private space using a two-gateway configuration, policies, traffic, and data are handled by separate ingress and egress Omni Gateways.
4 Collect logs, metrics, and traces from Omni Gateway and runtimes in Anypoint Monitoring.

Agent Network Assets in Anypoint Exchange

When you publish an agent network project to Exchange, the project becomes an agent network asset (a .zip of the project files), and the agentic assets in the project file register as agents or MCP servers. Brokers publish with the agent asset type and are tagged as brokers. An LLM asset records only the provider and contract. You set the model and connection in the agent network file. MCP server assets are defined as Tools in that file.

Agent network projects support several LLMs. For definitions of these asset types, see Agent Fabric Glossary. To learn more about the project files, see Agent Network YAML and Agent Script or Agent Network 2.0 Project File Reference.

Large Language Models

Agent network brokers support the latest models from OpenAI, Azure OpenAI, Bedrock OpenAI, and Gemini, as well as model proxies.

  • OpenAI

  • Azure OpenAI

  • Bedrock OpenAI

    Bedrock OpenAI uses the openai. prefix for model names (for example, openai.gpt-5.5), which differs from the model names used with OpenAI and Azure OpenAI.
  • Gemini

  • Model Proxy

    Agent network brokers only support access to OpenAI and Gemini through Omni Gateway Model Proxy. Transcoding other models to OpenAI format to use in agent networks is not supported.

This table details requirements and recommended models.

Model Provider Required Endpoint Required Capabilities Suggested Models

OpenAI

/responses

  • Reasoning

  • Native structured output

  • Function and custom tool calling

  • For lower latency: GPT-5-mini

  • For complex reasoning: Evaluate models

Gemini

/generateContent (Native API)

  • Native Thinking (via thinkingBudget and thinkingLevel)

  • Native structured output (responseSchema)

  • Function and custom tool calling

  • For lower latency: Gemini 2.5 Flash, Gemini 2.5 Flash-Lite

  • For complex reasoning: Gemini 3 Pro (Deep Think capabilities)

Agent networks support text-based messages and responses. Image and binary message types aren’t supported.

For configuration options, see the LLM Section of the Agent Script file reference.

A2A Protocol in Agent Networks

The Agent2Agent (A2A) Protocol governs agent-to-agent communication and powers orchestration, observability, and governance features in agent networks. For more information, see Use A2A Protocol in Agent Networks.