Automation and AI

MCP

Also called Model Context Protocol

An open standard, published by Anthropic, for connecting AI assistants to outside tools and data in one common format.

Quick facts: MCP

Category
Automation and AI
Also called
Model Context Protocol
Level
Advanced
Affects
Integration effort, tool portability, data access risk
Where to see it
AI assistants and IDEs with MCP support, published MCP servers for common business systems
In this article4
  1. How MCP works
  2. Why MCP matters
  3. Where MCP goes wrong
  4. How to act on it

How MCP works

Before a common standard existed, every connection between a model and a piece of software was built by hand for that pairing. Connect an assistant to your CRM, then to your analytics, then to your file store, and you had three bespoke integrations to write and maintain, all of them different.

The Model Context Protocol, published by Anthropic as an open standard, describes one way of doing that plumbing. Two sides are involved. An MCP server sits in front of a system — a database, a project tool, a set of files — and advertises what it offers: actions that can be run, data that can be read, and reusable instructions. An MCP client lives inside the assistant or agent and speaks to any server that follows the standard. Because both sides agree on the format, a server written once works with any client that supports it.

Why MCP matters

For a small business the appeal is practical rather than technical. It reduces the number of one-off integrations that have to be paid for and looked after, and it means a connector built for one assistant is not thrown away when you change assistant. That is the sort of thing that decides whether an AI setup is still working in two years.

It also puts a clear boundary around access. What an assistant may reach is defined by the servers you connect and the permissions those servers hold, rather than being buried inside a workflow. When someone asks what your AI tools can actually see, that list is the answer, and it is short enough to review.

Where MCP goes wrong

The clearest risk is installing servers casually. An MCP server is software running with real credentials to a real system, and connecting one from an unfamiliar source is the same decision as installing an unknown plugin on your website — except this one may be able to read customer data. Judge the source before the convenience.

The second is over-broad credentials. A server given full administrative access to your CRM will use exactly as much of it as it is asked to, so give each connection its own limited account.

The third is treating what a server returns as trustworthy. Content coming back from an outside system is data, not instruction, and an agent reading it should not be free to follow directions hidden inside it.

How to act on it

Connect what you actually need and no more. For each server, ask who wrote it, what credentials it holds, what it can change rather than only read, and where its activity is logged. Give it a dedicated account with the narrowest permissions the task allows, and review the list of connections on the same cycle as any other access review.

Treat it as one option, not a requirement: for many jobs an ordinary connection inside your workflow automation is simpler, and MCP earns its place when the same data must reach several different assistants. The underlying idea is still tool use; MCP only standardises how the tools are described.

Do and do not

Do

  • Vet who wrote a server before connecting it
  • Give each connection its own limited account
  • Review connected servers as you review access

Do not

  • Install an unfamiliar server for convenience
  • Hand a server administrator credentials
  • Let an agent obey instructions found in returned data

Questions people ask about this

Do I need MCP to use AI in my business?

No. Plenty of useful AI work happens through ordinary integrations in an automation platform, and those are often simpler to set up and easier to support. MCP becomes worth the effort when the same systems need to be reachable by several different assistants, because a connector built once can then serve all of them.

Is it safe to install an MCP server someone shared with me?

Treat it the way you would treat an unknown plugin on your website. It is software that runs with real credentials to a real system, so check who wrote it, what access it needs and whether it can change data or only read it. Give every connection its own limited account rather than an administrator login.

What is the difference between MCP and an ordinary API?

An API is how one specific system exposes its own functions, and every API is different. MCP is an agreed way of describing tools and data so that any compliant assistant can use them without a bespoke integration. An MCP server usually sits in front of an API and presents it in that common format.

Related terms

Found this useful?

Share it, or ask an AI to summarise it

Back to the glossary

Knowing the term is the easy part

Applying it to your own site and budget is the work. Book a call and I will tell you what actually applies to you.