AI Agents Inventory and Attributes - Relationship attributes for the AI Agents Inventory

AI Agents Inventory and Attributes

Chapter 33. Relationship attributes for the AI Agents Inventory

Authored and Published By: The International Foundation for Information Technology (IF4IT), LLC

Executive Summary: Chapter Overview

IF4IT

The Bottom Line

Relationship attributes capture the agent’s connective footprint as Derived and Calculated values — how many integrations, MCP servers, and data stores it reaches, how many tools it can invoke, and its key upstream and downstream dependencies. These roll up the agent’s edges in the Enterprise Model into a governable measure of its reach. Manually authored stakeholder and person-role relationships are governed in the Ownership and Stakeholder category, not here.

Core Concepts

Concept	Definition & Strategic Role
Connective footprint	A Derived/Calculated measure of how far the agent reaches across the estate.
Dependencies	The key upstream sources the agent relies on and downstream consumers that rely on it.

Quick Q&A

Question: What do relationship attributes add beyond the individual links?

Answer: They summarize the agent’s reach: an agent connected to many integrations, MCP servers, and data stores has a larger blast radius, and a Derived footprint makes that magnitude visible and comparable across the estate.

Read More Below

Relationship attributes summarize each agent’s connective footprint across the Enterprise Model as Derived and Calculated values.

Every attribute in this category is Calculated or Derived from records in other inventories. No manual data entry is required for any attribute in this category. Do not create data entry fields for any attribute listed here.

Attribute Name	Maturity	Description and Notes
Total Connected Integrations Count	Run	Description — The number of integrations the agent acts through. Benefit(s) — Quantifies the agent’s action surface and blast radius. Source — Calculated. Notes — Derived from the Integrations relationships.
Number of MCP Servers Connected	Run	Description — The number of MCP servers the agent connects to. Benefit(s) — Measures the agent’s tool-server reach. Source — Calculated. Notes — Derived from the MCP Servers relationships.
Total Data Stores Accessed	Run	Description — The number of distinct data stores the agent can access. Benefit(s) — Quantifies data reach for security and privacy impact analysis. Source — Calculated. Notes — Derived from the Data and Information relationships.
Count of Tools and Functions Available	Run	Description — The number of tools and functions the agent can invoke. Benefit(s) — Measures the breadth of actions the agent can take. Source — Calculated.
Key Upstream Dependencies [Multi-Value]	Run	Description — The critical models, systems, and data sources the agent depends on. Benefit(s) — Surfaces what the agent would fail without. Source — Derived. Examples — Primary LLM; Orders datastore
Key Downstream Dependencies [Multi-Value]	Run	Description — The systems, processes, and agents that depend on this agent. Benefit(s) — Surfaces what would be affected if the agent fails or is retired. Source — Derived. Examples — Billing process; Notification service

How to cite this page

When referencing this page in academic work, internal standards, or external publications, include the page title, IF4IT as author and publisher (The International Foundation for Information Technology (IF4IT), LLC), the URL, and your access date.

Example (informal web citation):

The International Foundation for Information Technology (IF4IT), LLC. Relationship attributes for the AI Agents Inventory | AI Agents Inventory and Attributes. https://if4it.org/best-practices/ai-agents-inventory-and-attributes/relationship-attributes-for-the-ai-agents-inventory/ (accessed 2026-07-23).

See About Us for content governance and site-wide citation guidance.

Legal Disclaimers

💡 The Bottom Line

📝 Core Concepts

🤖 Quick Q&A

How to cite this page

The Bottom Line

Core Concepts

Quick Q&A