Skip to content
deen
← All terms
Agents & automationLast reviewed

Model Context Protocol (MCP)

The Model Context Protocol (MCP) is an open standard through which AI applications access data and tools in a uniform way, such as files, databases or services.

Also known as: MCP

How it works

For an AI application to access files, databases or services, a separate integration used to be needed for every combination. MCP defines a common protocol for this: an MCP server provides tools and data, an AI application (the client) uses them in a uniform way. The standard was introduced by Anthropic, and many providers now support it.

A practical example

An assistant accesses calendar, document storage and ticket system through MCP servers without a custom solution being built for each tool.

What you should know

  • MCP simplifies integrations but does not replace permission management: check what a server may access.
  • Connect only trustworthy servers. A connected tool can read data and trigger actions.
  • The standard keeps evolving; features and adoption may change.

Matching tools

View all termsTo AI integration

From the blog

More on this from practice.

Articles from our blog that explain the term in context.

Artificial Intelligence

AI Agents in Everyday Work: Uses, Limits and Safety

What sets AI agents apart from chatbots and workflows, when which solution fits, which fields of use have proven themselves and which safety rules you need from the start.

Read on →

Related terms

More on the topic.

These terms are closely related to this entry.

Agents & automation

AI Agent

An AI agent is a system that pursues goals with a language model: it plans steps, uses tools such as search, databases or email, and checks intermediate results.

Learn more →

Agents & automation

Function Calling

In function calling, a language model does not output running text but a structured call to a function, which your application then runs — for example "create appointment".

To the definition →

Agents & automation

Workflow Automation

Workflow automation connects systems and work steps into processes that run automatically. With AI, unstructured inputs such as emails or documents can be processed as well.

To the definition →

Questions about your project?

Get in touch →