Skip to content
ESEN
Contact

Glossary · AI and automation

MCPModel Context Protocol

MCP (Model Context Protocol) is an open protocol that connects AI assistants and agents to external tools and data through a common interface, instead of a different integration for every case.

MCP: the details

Anthropic introduced it in November 2024, and since December 2025 it has been maintained by the Agentic AI Foundation, part of the Linux Foundation. It works with two pieces: an MCP server, which exposes what a system can do, and a client, which is the AI application using it. The server offers tools (actions the model can request), resources (data it can read) and prompt templates.

The practical advantage is that the integration is written once. An MCP server for your ERP works the same for Claude, for ChatGPT or for an agent of your own, and switching models doesn’t mean rebuilding it. The protocol doesn’t solve security by itself, starting with prompt injection: what each tool may do, with which credential and on which data is still a decision for whoever deploys it.

MCP in a project

We build MCP servers for internal systems—ERP, CRM, document management—with narrow permissions: read-only tools by default, writing only where a rule or a person confirms, and a log of every call. That way the same connector serves several assistants without handing out credentials.

On this site

Where we apply it

All services

Glossary

Related terms

See the whole glossary

Get started

Does this come up in your project?

Tell us which system you have and what is still done by hand. We’ll tell you where we would start and whether it fits.

Tell us about your project info@veodar.com

Before you write, see how we price a project or our solutions by department.

Fig. 07Morse keyH · E · L · L · O