Scan For AI Assets

AI Assets discovers components inside your connected environments with scans. Each scan runs against a selected environment and populates your AI inventory with newly discovered Models or AI Workflows. All scans are logged in Scan History for traceability.

Model Scans

Model scans analyze your connected environments to identify AI Models integrated into applications. Run Model scans regularly to stay updated on model usage across environments.

How to run a Model Scan

1. Navigate to AI Assets → Models.

2. Click Scan Models in the top right corner.

3. Select the environment(s) you want to scan.

4. Click Scan to begin.

Results appear in the Models view and include charts, usage breakdowns, and an updated model inventory.

Workflow Scans

Workflow scans analyze repositories for AI Workflows and their agents, tools, and MCP servers. Run Workflow scans whenever workflows or agentic architectures evolve.

How to run a Workflow Scan

1. Navigate to AI Assets → AI Workflows.

2. Click Scan AI Workflows in the top right corner.

3. Select the environment(s) you want to scan.

4. Click Scan to begin.

Results appear in the AI Workflows view, where workflows are visualized as interactive graphs showing architecture, dependencies, and connections.

MCP Servers Scan

MCP servers scans analyze repositories for MCP servers and their tools, prompts, resources, resource templates, and issues. Run MCP servers scans whenever server architectures evolve.

How to run a MCP Servers Scan

1. Navigate to AI Assets → MCP Servers.

2. Click Scan MCP Servers in the top right corner.

3. Select the environment(s) you want to scan.

4. Click Scan to begin.

Scan History

The Scan History page provides a full audit trail of all scans. Review Scan History to ensure full coverage and follow up on failed scans.

For each scan, you can see:

• Environment Name - the given environment name

• Environment Type - the type of environment scanned (currently GitHub or GitLab)

• Scan Type - whether the scan targeted Models, AI Workflows or MCP Server

• Created At - the timestamp of when the scan was initiated

• Status - scan state: Finished, In Progress, or Error

• Progress - scan completion percentage

• Assets Count - the number of AI components discovered

This allows teams to track discovery over time, verify coverage, and repeat scans as needed.

Figure 1: Scan History Page