Glossary

MCP (Model Context Protocol)

An open standard for connecting AI agents to tools and data, supported natively by Ngentix as server, client, and gateway.

The Model Context Protocol is the emerging open standard for connecting AI agents to the tools and data they need. It reduces the integration complexity of AI systems from quadratic to linear and is backed across the major AI labs.

Ngentix implements MCP as a first-class part of the platform: every connector it builds is automatically published as an MCP tool (server), it can consume external MCP servers as data sources (client), and it operates an MCP gateway that governs which agents can discover and call which tools.

Crucially, the tool descriptions are grounded in the Unified Data Model — an agent sees "Create Invoice" with full semantic context, not a raw "POST /api/v2/invoices".

Read next.

A2A (Agent-to-Agent Protocol) An open standard for AI agents to discover, delegate to, and collaborate with one another — supported natively by Ngentix. /glossary/a2a
Unified Data Model (UDM) A canonical schema of business entities and operations that lets the platform understand the meaning of the data it moves. /glossary/universal-data-model
Governance Engine The policy layer that controls and audits every action an agent or connector takes across the platform. /glossary/governance-engine

All terms · The analyses these terms come from