TechOneDigital Request an MCP architecture review

Based on the current stable MCP specification

What is MCP

What is MCP? The Model Context Protocol in plain terms.

MCP, the Model Context Protocol, is an open standard that lets AI applications connect to business systems in one consistent way. A system describes what it offers, such as data, actions and prompt templates, and any compatible AI application can discover and use it. MCP standardises the connection. It does not decide what the AI is allowed to do.

For

Management, IT leads and anyone new to MCP

Use when

You keep hearing about MCP and need to know what it changes before a decision.

Outcome

A shared vocabulary, the protocol basics and the questions MCP leaves to you.

Technical guide by , Founder & Technology Consultant.

TechOne architecture position

MCP is a connection standard, not a control system.

It makes connecting AI to systems easier and more uniform. Who may do what, which changes need a person to approve them, and how a mistake is noticed and reversed remain decisions your organisation has to design and enforce.

The problem MCP solves

Without a shared protocol, every AI application needs its own connector to every system.

Ten AI applications and ten business systems can mean a hundred separate integrations, each with its own credentials and failure behaviour. MCP replaces that with one protocol: a system is wrapped once as an MCP server, and any compatible AI application can use it. The specification compares this to the Language Server Protocol, which did the same for programming-language support in development tools.

Protocol basis: three roles

Host, client and server each have one job.

Host

The AI application a person uses: a chat assistant, a coding tool or an agent runtime.

Creates the clients, controls which connections are allowed, enforces security policy and consent, and handles the user’s authorisation decisions.

Client

A connector inside the host.

Each client talks to exactly one server and keeps the boundary between servers. A host usually runs several clients at once.

Server

A program in front of one system, for example a CRM, a ticketing tool or a file store.

Exposes that system’s capabilities. It can run as a local process or as a remote service. It receives only the context it needs and cannot see the whole conversation or other servers.

Protocol basis: what a server offers

Tools act, resources inform, prompts guide.

Tools

Functions the AI model can call, such as “create ticket” or “look up order status”. A tool can change data, so the specification treats tools as arbitrary code execution: hosts must obtain explicit user consent before invoking one.

Resources

Context and data that the user or the model can read, such as a document, a database record or a file.

Prompts

Templated messages and workflows that a user chooses to run, such as “summarise this incident”.

The direction can also reverse: a client may offer features to servers, for example elicitation, where a server asks the user for missing information.

Protocol basis: where a server runs

A local server and a remote server carry different risks.

Local server

  • Runs as a process on the user’s own machine, started by the host and connected over standard input and output (stdio).
  • Takes its credentials from the environment rather than from the MCP authorisation framework.
  • Runs with the privileges of that machine, so adding one is closer to installing software than to opening an account.
  • Typical for personal and developer tools.

Remote server

  • Runs as a network service that many users and applications can reach over HTTP (Streamable HTTP).
  • Protected with the OAuth-based authorisation framework the specification defines for HTTP.
  • Accepts only access tokens issued for that specific server and validates them on every protected request.
  • Typical for shared business systems that need central identity, logging and ownership.

Protocol basis: authorisation

Authorisation answers who may call a server. It does not answer whether this person may approve this payment.

Authorisation is optional in the core protocol. For servers reached over HTTP, the specification defines an OAuth-based model in which the MCP server acts as a resource server and checks an access token issued for it. The tools and resources a caller sees may depend on that authorisation. Business rules, such as which records a person may change or which amount needs a second approver, are not part of the protocol and have to be enforced by the server and the system behind it. Read the security and authorisation guide.

TechOne position

What MCP standardises, and what stays your decision.

The specification itself states that MCP cannot enforce its security principles at the protocol level; implementers are expected to build consent and authorisation flows and access controls around it.

MCP standardises

  • How AI applications discover what a system offers.
  • How a request and its result are exchanged.
  • The roles of host, client and server.
  • Authorisation for servers reached over HTTP.
  • Security principles such as user consent before a tool runs.

Your organisation still decides

  • Which operations a system exposes to AI at all.
  • Which person or agent may perform which action on which record.
  • Which changes need a human approval, and from whom.
  • What evidence is kept of each action and refusal.
  • How a failed or uncertain change is detected and reversed.
  • Which servers are approved for use, and who owns and operates each one.

Where to go next

From the basics to the architecture decisions.

Commercial route

Decide whether MCP belongs in your architecture.

Bring one use case. We start with the systems, identities, intended capabilities and consequences involved, not with a server or SDK choice.

Request an MCP architecture reviewExplore the complete MCP architecture

Primary sources

Protocol claims are grounded in official sources.

The source list distinguishes core protocol requirements, optional extensions and external implementation guidance. The surrounding enterprise control model is a TechOne architecture recommendation.

  1. Model Context Protocol specificationOverview: roles, server and client features, and the security and trust principles.
  2. MCP architectureHost, client and server responsibilities; local and remote servers; isolation between servers.
  3. MCP base protocolStateless requests and when the HTTP authorisation framework applies (HTTP versus stdio).
  4. MCP server featuresTools, resources and prompts exposed by servers.
  5. MCP authorizationOAuth-based authorisation for HTTP transports and audience-bound access tokens.
  6. Streamable HTTP transportThe HTTP transport used by remote servers.

Direct answers

Questions people ask when they first meet MCP.

Is MCP a product?

No. MCP is an open protocol with a public specification. Many AI applications and systems implement it; no single vendor owns its use.

Is MCP the same as an API?

No. An MCP server usually sits in front of a system’s existing API. The difference is that MCP describes its capabilities in a standard way, so any compatible AI application can discover and call them without a custom integration.

Does MCP make AI agents safe?

Not on its own. MCP carries requests and defines security principles, but the specification states that it cannot enforce them at the protocol level. Safety comes from the permissions, approvals, evidence and recovery designed around each server.

Do we need MCP for every AI project?

TechOne position: no. MCP pays off when several AI applications need the same systems, or when capabilities should be reusable and governed in one place. A single, narrow integration may not need it.

Should a server run locally or remotely?

TechOne position: local servers suit personal and developer tools tied to one machine. Shared business systems are usually better served by a remote server with central identity, logging and a named owner.

What should be decided before the first MCP server goes live?

Which operations it exposes, who may call each one, which actions need a human approval, what is recorded, and who owns and operates the server. The security and production guides cover each decision.