Glossary

Extensibility

What is Extensibility?

Extensibility is the ability of software to take on new functions, data sources or connections without rebuilding its core. Typical means are application programming interfaces (APIs), webhooks, plug-ins and open standards such as the Model Context Protocol (MCP). For businesses, an extensible AI solution works alongside existing systems such as a CRM or online shop and can grow with changing requirements.

How KI.ordo helps

KI.ordo can be connected to other software via a REST API, webhooks and an MCP server, making agents and flows available as tools for other AI applications.

Learn more →

Topics

Architecture
Interfaces
Integration

Try KI.ordo

Agents, flows and templates in one workspace – free 24-hour demo.

Start demo

← All terms

Related terms

Model Context Protocol (MCP)

The Model Context Protocol (MCP) is an open standard that lets AI applications access external tools, data sources and services in a uniform way. An MCP server provides functions, and an MCP client, such as an AI assistant, can call them. Anthropic introduced MCP in November 2024; since December 2025 it has been developed under the Agentic AI Foundation of the Linux Foundation (as of October 2026). This avoids building every integration separately.

interface
standard
+1

Remote MCP

Remote MCP refers to an MCP server that does not run locally on your own computer but is reachable over the internet via HTTP. The Model Context Protocol is an open standard that lets AI applications use external tools and data; for remote servers the specification provides the “Streamable HTTP” transport and authentication, for example via OAuth or an API key. The advantage is that a centrally hosted service is available to many users and AI programs without local installation.

MCP
interface
+1

AI Automation System

An AI automation system combines traditional process automation with AI capabilities such as understanding text, classification or decision support. This makes it possible to automate workflows with unstructured inputs too, such as emails, forms or enquiries. A typical setup is a chain of trigger, processing steps, conditions and output, with human approval at critical points. Example: incoming enquiries are automatically categorised, summarised and forwarded to the right department.

Automation
Processes
+1

No-code

No-code refers to tools that let people build applications, automations or websites through graphical interfaces without writing program code. Business teams can implement and test processes themselves instead of waiting for IT development. Limits appear with very specialised requirements, large data volumes or deep integrations. Example: a sales team uses drag and drop to build a flow that sorts and summarises new enquiries.

automation
tools
+1