Learn
Understanding the technology behind connected AI systems. Our technical reference for the Model Context Protocol—the open standard reshaping how businesses integrate AI with their tools.
How to Add an MCP Server to Claude Code
One command for hosted servers, one for local ones, plus scopes, sign-in, secrets and the errors you're most likely to hit.
Add MCP servers to Claude Code with claude mcp add: hosted servers over HTTP, local servers with npx or uvx, OAuth sign-in with /mcp, local vs user vs project scope, .mcp.json, and troubleshooting.
How to Add an MCP Server to Claude Desktop
Custom connectors for hosted servers, one-click desktop extensions, and claude_desktop_config.json for everything else.
Connect MCP servers to Claude Desktop three ways: custom connectors for hosted servers, desktop extensions (.mcpb), and claude_desktop_config.json for local servers. Config file locations, examples and fixes.
How to Add an MCP Server to Cursor
The mcp.json format for hosted and local servers, keeping keys out of the file, and switching servers on and off.
Set up MCP servers in Cursor with mcp.json: global vs project config, hosted servers with OAuth or API key headers, local servers with npx, ${env:} variables, envFile, and troubleshooting.
How to Add an MCP Server to VS Code
Add servers for GitHub Copilot's agent from the command palette or mcp.json, and use inputs to keep API keys out of your config.
Configure MCP servers in VS Code for GitHub Copilot agent mode: .vscode/mcp.json format, http, sse and stdio servers, MCP: Add Server, input variables for secrets, and fixes for common errors.
How to Use MCP Servers With ChatGPT
Developer mode, which plans can connect what, and what to do when the server you want only runs locally.
Connect MCP servers to ChatGPT with developer mode: which plans support it, how to add a hosted MCP server, why local servers need a hosted version or Secure MCP Tunnel, and managing write access safely.
Is ChatGPT Safe for Business Data? The Honest Answer for SMEs
The tool is rarely the problem — the tier and the habits are. Where the risk actually lives, and the five rules that make AI assistants safe for company data.
Is it safe to put business data into ChatGPT or Claude? What business tiers change about training and retention, what UK GDPR actually requires, the five rules that manage the risk, and why shadow AI use is the bigger exposure.
What Should an SME AI Policy Include? Seven Questions, One Page
The AI policy that works for a 10–200 person firm is a page long and answers seven questions. Here they are, with the wording that holds up.
How to write an AI policy for a small business: approved tools, the never-paste list, human review rules, decisions AI can't make, disclosure, incident reporting, and ownership — one page, seven sections.
How Much Does AI Automation Cost a Small Business? Real Numbers
The three tiers of AI spend — off-the-shelf tools, connected automation, and ongoing support — with actual price ranges and the arithmetic for deciding what's worth it.
AI automation costs for UK SMEs, with real numbers: £15–£60/user/month for assistants, £5,000–£25,000 for a connected build, and what support costs. What inflates the price and when to skip it.
What Is the Model Context Protocol? A Plain English Guide
The open standard that lets AI assistants like ChatGPT and Claude securely talk to your business software — explained without jargon.
Model Context Protocol (MCP) explained in plain English. Learn how this open standard lets AI assistants connect to your CRM, accounting tools, and databases securely.
MCP vs APIs vs Plugins: Which Integration Approach Should Your Business Use?
A clear comparison of the three ways to connect AI to your business tools — with guidance on when each one makes sense.
Compare Model Context Protocol, traditional APIs, and plugin ecosystems for AI integration. Learn which approach fits your business needs, budget, and technical resources.
How AI Assistants Connect to Your Tools: MCP Architecture Explained
A visual walkthrough of clients, servers, and the communication layer that makes AI integration work — from request to response.
Understand the technical architecture behind MCP: how AI clients communicate with MCP servers to securely access your business tools, databases, and APIs.
Where Should We Start With AI Automation? How to Pick the First Process
A practical guide for operational teams told to 'go do AI' — how to spot the right first process, score the candidates, and start where the risk is lowest.
How to choose your first AI automation project. Learn which processes make good candidates, what to avoid first, and a simple scoring exercise to shortlist where to begin.
What's the ROI of AI Automation — And How Do We Prove It?
Building the business case execs actually ask for — hard savings versus soft gains, a simple payback framework, and the ROI traps that sink credibility.
How to measure and prove the ROI of AI automation. Separate hard savings from soft gains, baseline before you build, model payback period, and avoid the common ROI traps.
Build, Buy, or Partner? Choosing How to Add AI to Your Operations
Off-the-shelf tools, in-house development, or a specialist partner — how to decide, the total cost and lock-in trade-offs, and a clear decision checklist.
Build vs buy vs partner for AI automation. Understand when off-the-shelf tools are enough, when you need custom integration, the hidden costs of ownership, and how to decide.
What Could Go Wrong? Governing AI Automation Without Killing It
The governance questions boards raise — data security, accuracy, human-in-the-loop, accountability — and the controls that let you move fast with your eyes open.
The real risks of AI automation — data exposure, hallucination, over-automation, accountability gaps — and the practical controls that govern them without slowing you down.
Looking for a deeper partnership? We handle the integration and implementation so you can focus on deploying AI at scale.
Explore AI Integration Services