Skip to content
← Back to the glossary

MCP (Model Context Protocol)

MCP is an open standard for how AI models connect to external data and tools in a secure, structured way.

Also known as: model context protocol

MCP (Model Context Protocol) is an open standard developed by Anthropic for how AI models connect to external data, tools, and systems. Instead of building custom integrations for every combination of AI model and system, MCP provides a common protocol for access control, authentication, and data formats. For businesses, this means AI agents can be connected to internal systems (SharePoint, databases, line-of-business systems) in a standardised way, with clear limits on what the agent can and cannot do. MCP is a recent standard (2024–2026) but has been adopted broadly very quickly.

Related terms

  • AI agent — An AI agent is software that sets goals, plans steps, and acts autonomously to achieve them — without continuous human oversight.
  • AI integration — AI integration is the process of wiring language models, RAG, or predictive models directly into a business's existing systems and workflows.
No commitment · 30 min · Free

We build what you need. Let's figure out what that is.

Send us two sentences about what's grinding. You'll hear back today, and we'll tell you whether this is something we can help with.

Send two sentences

Cookie settings

You can change these choices at any time. Necessary is always on because it is required for the site to work.

Necessary

Required for basic functionality, such as remembering your consent choice. No tracking.

Statistics

Anonymised visit statistics via Google Analytics 4. Helps us understand which pages people read.

Product insights

Detailed behavioural analysis via PostHog, including session recording with masked input fields. Used to improve the user experience.