# mulesoft Agent Visualizer - Full Documentation

<!-- document id=1cead4fc982f53dc6a0c44974144eac19a719644fa665f2ceb6c1239622fbdbd url=/mulesoft/current/en-us/agent-visualizer/agent-visualizer-components.md -->

---
product: Agent Visualizer
version: master
---

# Agent Visualizer Components

> For the full documentation index, see: https://docs.mulesoft.com/llms.txt

Use Agent Visualizer to identify the parts of your agent network and see how they work together.

- Distinguish node types (agents and MCP servers).

- View edges to see declared and runtime interactions.

- Use layers to focus views on specific environments

- Open details cards to inspect metadata and metrics for nodes and access logs and traces

- Review governance indicators such as Omni Gateway protection and applied policies.

## Node Types

Nodes in the agent network provide a visual representation of the agents and MCP servers within your
agent network including:

- [Agentforce agents](https://docs.mulesoft.com/agent-visualizer/agent-visualizer-glossary#agentforce-agent)

- [Agents](https://docs.mulesoft.com/agent-visualizer/agent-visualizer-glossary#agent)

- [Brokers](https://docs.mulesoft.com/agent-visualizer/agent-visualizer-glossary#broker)

- [MCP servers](https://docs.mulesoft.com/agent-visualizer/agent-visualizer-glossary#mcp-server)

For more information, see
[Viewing Node Details](https://docs.mulesoft.com/agent-visualizer/view-and-navigate-agent-network#viewing-node-details).

> [!NOTE] Agent Visualizer shows a maximum of 500 nodes. If you have more than 500 nodes, you won’t
> see all of them on the canvas. You can use search to locate specific nodes.

## Edges

Edges represent the relationships and communications among your nodes:

- Declared edges appear between node instances when no runtime information is available because
  there’s no registered traffic between them. Dashed lines on the graph indicate declared edges.

- Runtime edges appear between nodes when traffic is registered and a managed Omni Gateway exists.
  Solid lines on the graph indicate runtime edges. Click a runtime edge to open the details card and
  show the relevant metrics.

  Edges are drawn under specific conditions, primarily when the calling agent is protected by a
  managed Omni Gateway at egress. For agent-to-MCP relationships, edges are automatically drawn when
  the calling agent’s egress or the MCP server’s ingress is protected by a managed Omni Gateway. No
  new policies or extra configuration are needed to make edges visible. For more information, see
  [Deploying Agent Network Ingress and Egress Managed Omni Gateways](https://docs.mulesoft.com/gateway/latest/gateway-managed-ingress-egress)

- If an agent has an egress managed Omni Gateway, when it calls another agent, the edge is visible.

- If the requesting agent doesn’t have an egress Omni Gateway, no edge metric is generated and the
  edge isn’t shown.

- Broker agents that route outbound calls through an egress Omni Gateway, allowing requests between
  broker agents, or from a broker agent to an external agent, appear in the agent network
  visualization.

Selecting an edge opens the details card, which displays relationship information and metrics. For
more information, see [View Edge Details](https://docs.mulesoft.com/agent-visualizer/view-and-navigate-agent-network#view-edge-details).

## Data Flow Layers

Agent Visualizer provides a single, consistent architectural view of all assets defined in Exchange.
The base graph doesn’t change when toggling between production and non-production environments.

- Base graph

  - Always visible

  - Shows all assets defined in Exchange (agents and MCP servers) and their design‑time
    relationships from broker definitions

  - Topology and layout don’t change when switching layers

- Production layer

  - Overlays production instances and metrics on existing nodes and edges

  - Hides sandbox traffic lines

- Sandbox layer

  - Overlays sandbox instances (if they exist) and metrics on existing nodes and edges

  - Shows sandbox traffic as solid edges and hides production traffic lines

For more information about switching between production and sandbox environment layers, see
[View Data Flow Layers](https://docs.mulesoft.com/agent-visualizer/view-and-navigate-agent-network#view-data-flow-layers).

## Details Cards

The details card is the primary means for gaining detailed, 360-degree information about a selected
node or edge. It includes metadata and links to relevant resources like logs, policies, and more.

![Agent Visualizer details card showing metadata and links to relevant resources](/mulesoft/current/en-us/agent-visualizer/_images/agent-visualizer-details-card.png)

For more information, see [View Node Details](https://docs.mulesoft.com/agent-visualizer/view-and-navigate-agent-network#view-node-details).

### Node Metadata

When you select a node, the details card shows metadata for that agentic asset, including:

<table><colgroup><col> <col></colgroup><thead><tr><th>Field</th><th>Description</th></tr></thead><tbody><tr><td><div><div><p>Name</p></div></div></td><td><div><div><p>Name of the asset.</p></div></div></td></tr><tr><td><div><div><p>Description</p></div></div></td><td><div><div><p>Description of the asset.</p></div></div></td></tr><tr><td><div><div><p>Provider</p></div></div></td><td><div><div><p>Provider of the asset.</p></div></div></td></tr><tr><td><div><div><p>Platform</p></div></div></td><td><div><div><p>Platform of the asset, for example, Agentforce or MuleSoft.</p></div></div></td></tr><tr><td><div><div><p>LLM</p></div></div></td><td><div><div><p>LLM provider (for example, <code>OpenAI</code>).</p></div></div></td></tr><tr><td><div><div><p>Skills</p></div></div></td><td><div><div><p>Skills that are supported by the agent. Skills are concrete, callable operations within a capability, with defined input and output. For example,<code>lookupOrder</code>, <code>createCase</code>, <code>updateAddress</code>.</p></div></div></td></tr><tr><td><div><div><p>Linked Agents</p></div></div></td><td><div><div><p>Agents that are linked to the broker.</p></div></div></td></tr><tr><td><div><div><p>MCP Servers and Tools</p></div></div></td><td><div><div><p>MCP servers and tools that are connected to the broker.</p></div></div></td></tr><tr><td><div><div><p>Enabled Capabilities</p></div></div></td><td><div><div><p>Capabilities that are supported by the agent. Capabilities are high-level areas of what an agent can do (domains it supports, for example, customer support or knowledge search).</p></div></div></td></tr><tr><td><div><div><p>Instance Name</p></div></div></td><td><div><div><p>Instance name as it appears in API Manager.</p></div></div></td></tr><tr><td><div><div><p>Environment Type</p></div></div></td><td><div><div><p>Environments the instance is deployed to, for example, <code>sandbox</code> or <code>production</code>.</p></div></div></td></tr><tr><td><div><div><p>Based on Asset Version</p></div></div></td><td><div><div><p>Version of the instance.</p></div></div></td></tr><tr><td><div><div><p>Policies</p></div></div></td><td><div><div><p>Policies that are applied to the instance.</p></div></div></td></tr><tr><td><div><div><p>Governance and Security</p></div></div></td><td><div><div><p>Whether the asset is protected by an Omni Gateway.</p></div></div></td></tr><tr><td><div><div><p>Performance and Health</p></div></div></td><td><div><div><p>Performance and health metrics for the instance including:</p></div><div><ul><li><p>Successful Requests</p><div><p>This metric is shown for brokers, agents, and MCP servers. This is the total number of requests received successfully in the last 24 hours.</p></div></li><li><p>Failed Request Rate</p><div><p>This metric is shown for brokers, agents, and MCP servers. This is the percentage of requests that failed in the last 24 hours.</p></div></li><li><p>A2A Calls Sent</p><div><p>This metric is shown for brokers. This is the total number of messages sent to agents using the Agent2Agent (A2A) protocol in the last 24 hours.</p></div></li><li><p>MCP Calls Sent</p><div><p>This metric is shown for MCP servers. This is the total number of messages sent to MCP servers in the last 24 hours.</p></div></li></ul></div></div></td></tr><tr><td><div><div><p>Monitoring</p></div></div></td><td><div><div><p>Links to logs and traces for quick access to troubleshooting tools.</p></div></div></td></tr><tr><td><div><div><p>Tags</p></div></div></td><td><div><div><p>All tags associated with the asset in Exchange.</p></div></div></td></tr></tbody></table>

> [!NOTE] Broker metadata is defined in the agent network YAML. For more information about the agent
> network YAML, see
> [Defining Agent Networks](https://docs.mulesoft.com/agent-network/latest/af-define-your-agent-network-specification).

### Instance Information for an Agent

When you select an agent node, the details card shows environment-specific instance details for that
asset, including:

- Latest asset version

  The details card always shows the most recent (latest) asset version (highlighted) first, along
  with its corresponding instances in the selected environment (Production or Sandbox).

- All earlier versions

  All previous (earlier) instance versions are shown under the latest version.

  Each instance entry includes the asset version number, so you can easily distinguish between
  versions.

- Descending order of asset versions

  Instances are ordered from the most recent (latest) to least recent (earliest) asset version,
  making it easy to track version history over time.

### MCP Server Details

The MCP server details card includes active MCP tools and per‑instance activity.

- Active tools reflect the selected Activity Period and only include tools invoked during that
  window.

- Tools are aggregated across all instances of the MCP server, ranked by throughput, with the top 10
  displayed by default. Select **Show More** to view additional tools.

> [!NOTE] Publish MCP assets in Exchange before the tools are visible. Tools also require telemetry
> from a managed Omni Gateway on the relevant path. Runtime usage shows only allowlisted tools that
> have been called.

### Tool Details

When you select a tool, the tool details card opens. It shows:

- The tool name, icon, and MCP asset information at the top.

- A count of active instances (with traffic for this tool).

- A list of instances with per‑instance metrics (total calls and error rate) for the selected tool.

## Policy Visualization

The policy visualization shows nodes that are protected by an Omni Gateway indicated by a shield
icon. Data about applied policies comes from API Manager.

You can see the details of applied policies in the details card for the selected node.

## See Also

- [Agent Visualizer Overview](https://docs.mulesoft.com/agent-visualizer/)

- [Viewing and Navigating Your Agent Network in Agent Visualizer](https://docs.mulesoft.com/agent-visualizer/view-and-navigate-agent-network)

- [Getting Started with Agent Networks](https://docs.mulesoft.com/agent-network/latest/af-get-started)

- [Anypoint Monitoring Overview](https://docs.mulesoft.com/monitoring/)

- [API Manager 2.x](https://docs.mulesoft.com/api-manager/latest/)

- [Anypoint Exchange Overview](https://docs.mulesoft.com/exchange/)

- [Agent Visualizer Glossary](https://docs.mulesoft.com/agent-visualizer/agent-visualizer-glossary)

<!-- document id=3fd08ef9e350cb6aab0584f3c47b8d69b60695998dd7e9ef17d5d67b59808e61 url=/mulesoft/current/en-us/agent-visualizer/agent-visualizer-glossary.md -->

---
product: Agent Visualizer
version: master
---

# Agent Visualizer Glossary

> For the full documentation index, see: https://docs.mulesoft.com/llms.txt

Agent

An autonomous software component that uses goals, context, and available tools, often via a large
language model (LLM), to decide and execute actions on behalf of a user or system.

Agent network

An agent network is a collection of agents, brokers, LLMs, and MCP servers that are connected to
each other.

For more information, see
[Building Agent Networks for Agent Fabric](https://docs.mulesoft.com/agent-network/latest/af-agent-networks).

Agentforce agent

An agent that originates from Agentforce.

For more information, see [Agentforce](https://www.salesforce.com/agentforce/).

Broker

An intelligent routing service that coordinates task delegation across specialized agents in your
enterprise. Brokers originate from MuleSoft and are referenced in the agent network YAML.

For more information, see
[Defining Agent Networks](https://docs.mulesoft.com/agent-network/latest/af-define-your-agent-network-specification)

Declared edge

A design‑time relationship between two nodes (from the agent network YAML or Exchange metadata)
indicating an intended connection. When no runtime traffic is observed, it’s rendered as a dashed
line.

For more information, see [Edges](https://docs.mulesoft.com/agent-visualizer/agent-visualizer-components#edges).

Managed Omni Gateway

An Omni Gateway that is managed by Anypoint Platform.

For more information, see [Managed Omni Gateway](https://docs.mulesoft.com/gateway/latest/#managed).

MCP Server

A service that implements the Model Context Protocol (MCP) to expose tools and data to AI clients,
enabling LLMs to invoke external capabilities through a standard interface.

Runtime edge

A live relationship that’s drawn when actual traffic is observed between two nodes (from Omni
Gateway or Monitoring telemetry). It’s rendered as a solid line in the agent network.

For more information, see [Edges](https://docs.mulesoft.com/agent-visualizer/agent-visualizer-components#edges).

## See Also

- [Agent Visualizer Overview](https://docs.mulesoft.com/agent-visualizer/)

<!-- document id=ff3f4af21986b33060cfacbc474d04823dc79aafcb2496f5cbadbe8320583d8d url=/mulesoft/current/en-us/agent-visualizer/index.md -->

---
product: Agent Visualizer
version: master
description: Agent Visualizer maps your enterprise agent network in real time, showing connections between agents, MCP servers, LLMs, and external platforms including Amazon Bedrock, Microsoft Copilot, and Google Vertex AI.
---

# Agent Visualizer Overview

> For the full documentation index, see: https://docs.mulesoft.com/llms.txt

Agent Visualizer provides a detailed visual graph of your agent network so you can see, understand,
and interact with your enterprise’s evolving network of agents, Model Context Protocol (MCP)
servers, and large language models (LLMs). Agent Visualizer gives you insight into hidden agent
interactions, governance gaps, and performance bottlenecks.

Agent Visualizer supports agents created in external platforms including Amazon Bedrock, Microsoft
Copilot, and Google Vertex AI.

With Agent Visualizer, you can:

- View all connected agents, MCP servers, and LLMs on a single map, including relationships and
  direction of calls.

- View real-time call volume between agents and MCP servers to identify key pathways and under- or
  overused connections.

- Identify which agents lack Omni Gateway policy coverage to spot governance gaps.

- Select any node to view its purpose, origin, and all active running instances.

- Filter traffic by production and nonproduction environments.

![Agent Visualizer graph showing a network of agents](/mulesoft/current/en-us/agent-visualizer/_images/agent-visualizer.png)

## Agent Visualizer Use Cases

Use Agent Visualizer to gain clarity and control over your agent ecosystem.

- Discover your agent landscape.

  Architects and platform teams can view a complete network graph of enterprise agents to map
  dependencies, plan integrations, and eliminate shadow IT.

- Monitor real-time usage.

  Developers can validate adoption and consumption patterns by overlaying real-time transaction
  traffic, helping them optimize performance and capacity.

- Assess security and compliance coverage.

  Security teams can visualize active policies across the network to verify enforcement, spot
  vulnerabilities, and make sure regulatory compliance.

- Troubleshoot failures faster.

  Operators can trace dependencies, isolate failing nodes, and deep-link into service logs for rapid
  incident response and root cause analysis.

## Before You Begin

Before getting started, make sure you have:

- An Anypoint Platform account

- Required [Agent Visualizer permissions](#av-permissions)

## Agent Visualizer Permissions

<table><colgroup><col> <col> <col></colgroup><thead><tr><th>To…​</th><th>Required Permission</th><th>Notes</th></tr></thead><tbody><tr><td><div><div><p>View monitoring data for agentic assets.</p></div></div></td><td><div><div><p>Anypoint Monitoring: Monitoring Viewer</p></div></div></td><td><div></div></td></tr><tr><td><div><div><p>View agentic assets.</p></div></div></td><td><div><div><p>Exchange: Exchange Viewer</p></div></div></td><td><div></div></td></tr><tr><td><div><div><p>View API nodes and relationships.</p></div></div></td><td><div><div><p>API Manager: View APIs Configuration</p></div></div></td><td><div></div></td></tr><tr><td><div><div><p>View policies for assets.</p></div></div></td><td><div><div><p>API Manager: View Policies</p></div></div></td><td><div></div></td></tr></tbody></table>

## See Also

- [Anypoint Monitoring](https://docs.mulesoft.com/monitoring/)

- [Anypoint Exchange](https://docs.mulesoft.com/exchange/)

- [Anypoint API Manager](https://docs.mulesoft.com/api-manager/latest/)

- [Agent Fabric](https://docs.mulesoft.com/general/learning-map-agent-fabric)

- [MCP Server](https://docs.mulesoft.com/mulesoft-mcp-server/)

- [Anypoint Code Builder](https://docs.mulesoft.com/anypoint-code-builder/)

- [Agentforce](https://www.salesforce.com/agentforce/)

- [Glossary](https://docs.mulesoft.com/agent-visualizer/agent-visualizer-glossary)

<!-- document id=2354253d7200eaf634ddcd6b361742e4e48f7c42feca1ad0096e32b14afb3315 url=/mulesoft/current/en-us/agent-visualizer/agent-visualizer-release-notes.md -->

---
product: Agent Visualizer
version: master
---

# Agent Visualizer Release Notes

> For the full documentation index, see: https://docs.mulesoft.com/llms.txt

Agent Visualizer provides a detailed visual graph so you can see, understand, and interact with your
enterprise’s evolving network of agents, Model Context Protocol (MCP) servers, and LLMs.

## April 29, 2026

### What’s New

These Agent Visualizer features are now available in Canada Cloud and Japan Cloud.

<table><colgroup><col> <col></colgroup><thead><tr><th>Category</th><th>Feature</th></tr></thead><tbody><tr><td rowspan="3"><p>Observability</p></td><td><p>Agent Visualizer nodes</p></td></tr><tr><td><p>Agent Visualizer runtime edges</p></td></tr><tr><td><p>Agent Visualizer: Agent Metrics</p></td></tr></tbody></table>

For details, see [Hyperforce Release Notes](https://docs.mulesoft.com/release-notes/hyperforce/hyperforce-release-notes).

## February 9, 2026

### What’s New

- MCP server and tool insights

  Visualize agent and MCP server relationships to identify active tools ordered by throughput and
  drill down into specific tools to review instance counts, total calls, and error rates.

- Advanced search capabilities

  Locate specific nodes instantly using case-insensitive search by display name, asset type, or
  platform.

- Granular network filtering

  Isolate specific traffic patterns by filtering your agent network view based on business groups,
  environments (Production or Sandbox), and activity periods.

For more information, see [View and Navigate the Agent Network](https://docs.mulesoft.com/agent-visualizer/view-and-navigate-agent-network).

## October 3, 2025

### What’s New

- This is a new product that provides a visual map of your agent network.

  For more information, see [Agent Visualizer Overview](https://docs.mulesoft.com/agent-visualizer/).

## See Also

- [Agent Visualizer Overview](https://docs.mulesoft.com/agent-visualizer/)

- [Troubleshooting Your Agent Network in Agent Visualizer](https://docs.mulesoft.com/agent-visualizer/troubleshoot-agent-network)

- [Known Issues](https://help.salesforce.com/s/issues)

<!-- document id=30d9a3d5d7d4b040c5215b4bc30a01c86909cda5f377bc76d5653885ad59ba21 url=/mulesoft/current/en-us/agent-visualizer/node-governance.md -->

---
product: Agent Visualizer
version: master
---

# Governing Nodes in Agent Visualizer

> For the full documentation index, see: https://docs.mulesoft.com/llms.txt

See which nodes in your agent network are protected and which policies are applied. Open the asset
in API Manager to review more details about its policies. If a node isn’t protected, you can add a
managed Omni Gateway and create the appropriate instance to enforce policies.

## View Node Policies

1.  Look for the shield icon on nodes to see which nodes are secured by Omni Gateways.

2.  Click the node to open the details card and see the policies that are applied to the node.

3.  Click **View Policies** to view the policies for this instance in API Manager.

    Policies are listed by category on the left and applied policies are listed on the right.

## Add an Omni Gateway

Add a managed Omni Gateway to the node to enforce authentication, rate limits, and other policies at
ingress and egress, and to emit telemetry for monitoring and visualization.

1.  Click the node to open the details card.

2.  Click **Add Omni Gateway**.

3.  In API Manager, add an instance of the asset (MCP server or agent) to protect.

    For information about adding an MCP server or agent instance, see
    [Add an Omni Gateway Agent or Tool Instance](https://docs.mulesoft.com/api-manager/latest/create-instance-task-agent-tool).

## See Also

- [Agent Visualizer Overview](https://docs.mulesoft.com/agent-visualizer/)

- [Viewing and Navigating Your Agent Network in Agent Visualizer](https://docs.mulesoft.com/agent-visualizer/view-and-navigate-agent-network)

- [Omni Gateway Overview](https://docs.mulesoft.com/gateway/latest/)

<!-- document id=5ed4f9a531a7c80df24781c8d42e16c72472ede07c01aa5823f124b860a1507b url=/mulesoft/current/en-us/agent-visualizer/troubleshoot-agent-network.md -->

---
product: Agent Visualizer
version: master
---

# Troubleshooting Your Agent Network in Agent Visualizer

> For the full documentation index, see: https://docs.mulesoft.com/llms.txt

Use Agent Visualizer with Anypoint Monitoring to diagnose issues across agents and MCP servers. Open
a node’s details card to see associated metrics and access logs and traces in Anypoint Monitoring.

## View Metrics

The details card for a node includes a **Performance and Health** section with metrics. You can also
view additional metrics in Anypoint Monitoring.

1.  Select a node to open the details card.

2.  In **Performance and Health**, click **View Metrics** to view additional metrics in Anypoint
    Monitoring.

For more information, see [Monitoring Agentic Assets](https://docs.mulesoft.com/monitoring/anypoint-insights-agentic).

## Access Logs

You can access and view logs for an asset instance in Anypoint Monitoring or API Manager, depending
on your organization’s Anypoint Platform subscription.

1.  Click the node to open the details card.

2.  Click **View Logs** to access the logs for the node.

    Instance-specific logs for the agent or MCP server are shown.

    If your organization has the Anypoint Integration Advanced package or a Titanium subscription to
    Anypoint Platform, you can view the logs for the asset instance in Anypoint Monitoring. For more
    information, see [Get Logs for Agentic Assets](https://docs.mulesoft.com/monitoring/logs-search-hf#search-agentic).

    If your organization doesn’t have the Anypoint Integration Advanced package or a Titanium
    subscription to Anypoint Platform, you can view the logs for the asset instance in API Manager.
    For more information, see
    [Viewing Managed Omni Gateway Runtime and Access Logs in Anypoint Monitoring](https://docs.mulesoft.com/gateway/latest/managed-view-logs-in-monitoring).

## Access Traces

> [!NOTE] This beta feature is available only if your organization has the Anypoint Integration
> Advanced package or a Titanium subscription to Anypoint Platform.

For more information, see [Examining Traces](https://docs.mulesoft.com/monitoring/traces).

1.  Click the node to open the details card.

2.  Click **View Traces** to access the traces for the node.

    Anypoint Monitoring opens and you can view the **Traces Details** page for the asset instance.

## See Also

- [Using Logs in Anypoint Monitoring](https://docs.mulesoft.com/monitoring/logs)

- [Examining Traces](https://docs.mulesoft.com/monitoring/traces)

- [Known Issues](https://help.salesforce.com/s/issues)

<!-- document id=2853105afc6ea8d9b3f9fa1048d3cdb8aea8b5247db170579d136da2938a00e2 url=/mulesoft/current/en-us/agent-visualizer/view-and-navigate-agent-network.md -->

---
product: Agent Visualizer
version: master
---

# Viewing and Navigating Your Agent Network in Agent Visualizer

> For the full documentation index, see: https://docs.mulesoft.com/llms.txt

Explore an interactive map of agents, brokers, and Model Context Protocol (MCP) servers. Pan and
zoom, filter by environment, toggle layers, and select nodes or edges to view detailed metadata,
metrics, and links for deeper investigation.

## Before You Begin

You need these Anypoint Platform permissions to access Agent Visualizer:

- Monitoring: Monitoring Viewer

- Exchange Viewer

- API Manager View: View API Configuration

- API Manager View: View Policies

## Access Agent Visualizer

1.  Log in to Anypoint Platform.

2.  Click **Agent Visualizer > Get Started**.

    On the Agent Visualizer page, you see the agent network map showing all discovered agentic
    assets, nodes and their relationships (edges).

If the page is empty, there are no discoverable agentic assets in Anypoint Exchange (Exchange). For
more information about creating an agent network project and publishing assets to Exchange, see
[Creating Agent Networks](https://docs.mulesoft.com/agent-network/latest/af-create-agent-network).

## Navigate the Agent Network

Agent Visualizer provides an interactive view of your agent network where you can zoom in and out,
click and drag on the canvas to pan the visualization, and turn on environment layers (production or
nonproduction) to see additional views.

## View and Toggle Data Flow Layers

Use data flow layers to switch the runtime view between production and sandbox environments. The
base graph (assets and design‑time relationships from Exchange and broker definitions) stays the
same; only instance‑level metrics change.

1.  Leave the toggle on **Production environments** (default).

    ![Toggle set to production environments](/mulesoft/current/en-us/agent-visualizer/_images/agent-visualizer-layers-toggle.png)

    Production instances and their metrics appear on the existing nodes and edges.

2.  Switch the toggle to **Sandbox environments**.

    Sandbox instances and their metrics appear on the same nodes and edges. When viewing sandbox,
    production traffic lines are hidden and sandbox traffic lines are shown as solid edges.

For more information about the data flow layers, see
[Data Flow Layers](https://docs.mulesoft.com/agent-visualizer/agent-visualizer-components#data-flow-layers).

## View Node Details

When you select a node, a details card opens to provide comprehensive information for the asset.

> [!NOTE] Agent Visualizer shows a maximum of 500 nodes. If you have more than 500 nodes, you won’t
> see all of them on the canvas. You can use search to locate specific nodes.

1.  Select any node in the agent network (or press Enter or Spacebar after focusing the node with
    arrow keys) to show its details card.

2.  Review the node details.

For more information about the metadata you see for a node, see
[Node Details](https://docs.mulesoft.com/agent-visualizer/agent-visualizer-components#details-card).

## View Edge Details

The edge is shown as a solid line if traffic is observed between the nodes in the last 24 hours. The
edge is shown as a dashed line if traffic is not observed between the nodes in the last 24 hours.
See [Edges](https://docs.mulesoft.com/agent-visualizer/agent-visualizer-components#edges) for more information.

When you select an edge, the details card displays relationship information and metrics. Metrics are
aggregated for all instances that exist between nodes.

1.  Select an edge to open its details card.

2.  Examine the traffic throughput per hour.

## View External Agents and MCP Servers

External agents and MCP servers that are published to Exchange appear as nodes in the agent network.
You can select these nodes to view metadata and, when available, instance details.

1.  To open its details card and review the node’s metadata, select an external agent or MCP server
    node.

    > [!NOTE] To visualize runtime edges for external agents, see
    > [View Agents Without Omni Gateway](#view-standalone-agents).

## View MCP Server Edges and Tools

When agents invoke MCP servers, Agent Visualizer shows the relationship on the graph and lists MCP
tools on the MCP server node’s details card.

1.  Select an MCP server node to focus associated edges and open its details card.

    Tool invocations from multiple agents are aggregated into a single list on the MCP server node.

    - Tools are ordered by throughput (total MCP calls).

    - The top 10 tools are shown by default.

      Click **Show More** to see additional tools when available.

      > [!NOTE] For tool visibility, the MCP server is present in Exchange and the egress path is
      > protected by a managed Omni Gateway. This applies to MuleSoft‑hosted MCP servers defined in
      > the broker network and externally hosted MCP servers defined in the broker network.

      The tools list reflects the selected activity period and shows only tools that were invoked
      during that window. Allowlisted tools that aren’t called don’t appear. If the MCP server
      exposes a tool catalog that Agent Visualizer can query, the details panel shows the full set
      of available (design‑time) tools alongside runtime usage.

2.  To see traffic metrics on the connection, select the edge between the agent and the MCP server
    and open the edge details card.

### Example: Visualize Interactions Between External Agents and MCP Servers

To visualize runtime edges for external agents and MCP servers that aren’t part of a defined agent
network, publish them to Anypoint Exchange as agents or tools and route their traffic through Omni
Gateway.

This example shows how to visualize the interactions between agents and MCP servers when they aren’t
part of an agent network. This process manually "onboards" your external assets so they appear in
the agent network graph as managed nodes with live traffic edges.

1.  Publish your agents and MCP servers to Anypoint Exchange.

    For more information about creating assets in Exchange, see
    [exchange::to-create-an-asset.adoc#create-mcp](https://docs.mulesoft.com/exchange/to-create-an-asset#create-mcp).

2.  Set up an Omni Gateway in Connected Mode.

    To enable visualization, both the calling agents and the MCP servers are governed by Omni
    Gateway. By routing traffic through a gateway endpoint instead of calling the server directly,
    the gateway intercepts the request, injects identity headers, and reports the interaction to the
    Agent Visualizer.

    For more information about securing agent interaction in Omni Gateway, see
    [Securing Agent Interactions with Omni Gateway](https://docs.mulesoft.com/gateway/latest/agent-secure).

3.  In API Manager, create a new instance for each MCP server.

    1.  Point the Implementation URI to the actual external URL of your MCP server.

    2.  Deploy these instances to your egress Omni Gateway.

4.  Enable telemetry by injecting identifying headers for visualization (for example, source and
    destination identifiers).

    1.  In API Manager, go to the **Policies** tab for these instances.

    2.  Apply the Agent Connection Telemetry policy. This allows the gateway to parse MCP-specific
        traffic (like list tools).

    3.  Record the Consumer URL (the Omni Gateway endpoint) for each MCP server.

5.  Publish the agent asset in Anypoint Exchange with the **Agent** type.

6.  Set up the ingress Omni Gateway to handle the inbound traffic to the agent.

7.  In API Manager, go to **Agent and Tools Instances** and select **Add > Agent**.

    1.  Assign the agent to the Ingress Omni Gateway.

    2.  Copy the Agent Instance ID.

        The external agent uses this ID to identify itself to the Ingress Omni Gateway.

8.  In API Manager, apply a **Header Injection** policy to the agent instance.

    1.  Add the **Header Name** as `x-agent-instance-id` and the **Header Value** as the Agent
        Instance ID you copied earlier.

    2.  Click **Apply**.

9.  On the calling agent app, inject the `x-anypoint-api-instance-id` header (on list tools or call
    tools operations) providing the agent Instance ID from the ingress entry in API Manager as the
    value of the header.

## View Agents Without Omni Gateway

Agents that aren’t protected by a managed Omni Gateway appear as standalone nodes. You can still
view their metadata and understand their purpose in the network.

1.  Select the agent node to open its details card.

    Review metadata, tags, and any instance details available.

2.  To visualize runtime edges and performance metrics, protect the agent with a managed Omni
    Gateway on the relevant path (ingress or egress), then generate traffic.

## Search the Agent Network

Use search to locate nodes in the agent network. Search is case‑insensitive and supports multiple
fields. Search results reflect the current base graph. The environment layer you select (Production
or Sandbox) affects instance‑level metrics but not which nodes you can find with search.

1.  Open the search box.

    Show me how

    - Click the magnifying glass icon.

    - Use the keyboard shortcuts:

      - Mac: Cmd+Shift+k

      - Windows: Ctrl+Shift+k

2.  Enter your search terms.

    You can search by:

    - Display name

    - Asset type, for example, broker, agent, MCP

    - Platform, for example, MuleSoft, Agentforce, AmazonBedrock

    - Exchange tags

      Smart suggestions show up to 10 results, ordered by relevance, with Type and Platform badges
      and an indicator of the matched field.

3.  To zoom in on the node and open its details card, select a result.

4.  To clear the results and close the search box, press the escape key.

## Add Filters

Use filters to control which parts of the network you see on the canvas. Filters help you focus on
the information you need in large graphs by limiting the scope to specific business groups and time
windows.

The agent network graph shows assets that belong to the selected business groups, and the same map
shows edges between those assets (including cross‑business group connections).

Metrics on nodes and edges are aggregated based on the business groups you select. When you deselect
business groups, metrics update to reflect only the remaining selection.

### Apply Filters to the Agent Network

1.  Open the filter panel and select the filters to apply:

    - **Business Groups**

      By default, your current business group is selected. You can select multiple business groups
      to see cross-business group connections in a single view. Only business groups you have Agent
      Visualizer permissions for appear in the list.

      When you select multiple business groups, the canvas shows assets belonging to the selected
      business groups and edges between those assets across all selected business groups. Metrics
      are aggregated across all selected business groups. When you deselect business groups, metrics
      update to reflect only the remaining selection.

      > [!TIP] If performance degrades when viewing multiple business groups at once, reduce the
      > selection, use search, or zoom to areas of interest.

    - **Environment**

      Select **Production** or **Sandbox**.

    - **Activity Period**

      Select the last: ****24 hours**** **3 days** ****5 days**** **7 days**

    - **Display Options**

      You can hide standalone nodes and edges.

2.  Click **Apply Filters**.

## See Also

- [Agent Visualizer Overview](https://docs.mulesoft.com/agent-visualizer/)

- [Agent Visualizer Components](https://docs.mulesoft.com/agent-visualizer/agent-visualizer-components)

- [Governing Nodes in Agent Visualizer](https://docs.mulesoft.com/agent-visualizer/node-governance)

- [Getting Started with Agent Networks](https://docs.mulesoft.com/agent-network/latest/af-get-started)

- [Creating Agent Networks](https://docs.mulesoft.com/agent-network/latest/af-create-agent-network)