Guides to MCP, skills and AI tools in practice
Long-form, regularly updated explainers on the technology behind today's AI agents. Written by the team that runs it inside the EU for European companies.
AI agents and agentic AI
What agents are, how they differ from chatbots, how they work, and what it takes to run them safely in a company.
What is agentic AI? Agents, autonomy and how they differ from generative AI
Agentic AI is AI that pursues a goal by planning, using tools and checking its own results, rather than answering a single prompt. Here is what an AI agent actually is, how agents work under the hood, how they differ from chatbots and RPA, where they are used, and what it takes to run them safely in a company.
Read the guide →How to build AI agents: a practical guide from first job to production
How to build an AI agent that does real work: define the job and success criteria, pick a model, give it tools through MCP, write its instructions, add guardrails and evaluation, and choose between no-code builders, agent SDKs and a managed gateway. With a worked example.
What is AI governance? A practical definition, the building blocks and how to start
AI governance is how an organisation decides which AI it uses, for what, with which data, and who is accountable. This guide defines it, explains why it matters now, lists the building blocks, maps the EU AI Act, NIST AI RMF and ISO/IEC 42001, and gives a 30/60/90-day plan to start.
Claude Managed Agents: what it is, what it costs and when to use it
Claude Managed Agents is Anthropic's hosted agent harness: agents, environments, sessions and events, built-in tools, MCP servers and permission policies. Here is how it works, what a session costs, where the data lives, and what a European company should check before putting it in production.
Model Context Protocol
The open standard that lets AI models use tools and data. What it is, how it works, and how to run it securely.
Model Context Protocol (MCP): the complete guide
What MCP is, why it exists, how hosts, clients and servers fit together, what the protocol actually sends over the wire, and how to run it safely in a company. Updated for the 2026 ecosystem.
Read the guide →What is an MCP server? A plain-language explainer with an example
An MCP server is a small program that gives an AI model access to tools and data through the Model Context Protocol. Here is what it does, what it looks like, how to connect one, and when to write your own.
MCP security best practices: the threat model and a checklist
The Model Context Protocol gives AI agents real access to real systems. Here are the attacks that have actually happened, why they work, and the controls that stop them, from server allowlists to treating every tool result as untrusted input.
What is an MCP gateway, and when do you need one?
An MCP gateway is a single control point between AI clients and MCP servers: allowlists, per-user tool policy, credential injection, regional hosting and a full log. Here is what it does, when a company needs one, and what to look for.
The best MCP servers for teams in 2026
The MCP servers that show up in real company rollouts, grouped by what they connect to, with notes on hosting, scopes and what to watch for. Developer tools, project management, data, browser automation and infrastructure.
Best MCP servers for marketing and SEO: Google Ads, GA4, Search Console, HubSpot, Ahrefs and more
The MCP servers that let an AI agent work with your marketing stack: ads platforms, analytics, search data, CRM and CMS. What each one does, whether it is official, what it can write, and how to run them without handing an agent your ad budget.
Claude connectors explained: the list, what data they can access, and how MCP works underneath
Connectors let Claude read and act on Gmail, Google Drive, Slack, GitHub, HubSpot, Notion and dozens of other tools. This guide covers what connectors are, how they differ from MCP servers (they are MCP servers), which ones exist, exactly what data Claude can see, how to add a custom connector, and what enterprise admins control.
Google Search Console MCP: give Claude your search data
How to connect an AI assistant to Google Search Console through MCP: what servers exist, setting up a service account, which questions the agent can then answer (queries, pages, positions, indexing), and how we run ours.
Google Ads MCP: what the official server does, how to set it up, and where it stops
Google publishes an official, read-only Google Ads MCP server. This guide covers the prerequisites (developer token, OAuth or service account, customer IDs), the setup, what an agent can analyse with GAQL, why it cannot change campaigns, and how we handle writes safely.
Salesforce MCP: the official servers, the community ones, and what an agent can do with your CRM
Salesforce offers MCP in two official forms, the DX server for developers and hosted servers for business data, plus community servers over SOQL and REST. What each covers, how to set them up, and how to keep an agent from deleting your pipeline.
HubSpot MCP server: setup, tools, and what a marketing agent can do with it
HubSpot runs an official remote MCP server with OAuth. This guide covers how to connect it from Claude, Claude Code and Cursor, which objects and tools it exposes, useful workflows for marketing and sales, and how to control writes.
Google Analytics MCP server: set up Google's official GA4 MCP in Claude, step by step
Google's official GA4 MCP server (analytics-mcp) is read-only and runs locally. Exact setup commands for Claude Code, Claude Desktop and Cursor, the gcloud scopes that trip most people up, all seven tools, and the questions that make it useful.
Shopify MCP: Dev MCP, Storefront MCP and Admin access explained
Shopify ships two official MCP servers, one for developers building on the platform and one every store exposes for shopping agents, plus community servers for admin operations. What each is for, how to set them up, and what an agent can safely do in a store.
Ahrefs MCP: a keyword research API inside Claude, setup and what it costs in API units
Ahrefs runs an official MCP server over its keyword research API (API v3). How to add it to Claude Code, Claude Desktop and Cursor, what it exposes, how it compares with calling a keyword research API directly, a workflow that works, API unit costs, and running it from Europe.
Google Tag Manager MCP: what exists, how to set it up, and why publishing needs a human
There is no official Tag Manager MCP server, but community servers over the GTM API let an agent read containers, tags, triggers and variables, audit consent setup, and in some cases create versions and publish. What they can do, how to authenticate, and how to keep an agent from publishing a broken container.
How to add an MCP server to Claude Code
Add local and remote MCP servers to Claude Code with claude mcp add, choose the right scope (local, project or user), authenticate remote servers with /mcp, share servers with your team through .mcp.json, and route everything through a gateway for company use.
How to add an MCP server to Cursor
Configure MCP servers in Cursor through the settings UI or mcp.json, at project or global level, with the config format for local and remote servers, one-click install links, authentication, and how to standardise servers across a team.
How to add an MCP server to Claude Desktop
Three ways to give Claude Desktop a tool: connectors from the directory, custom connectors by URL, and local MCP servers through claude_desktop_config.json or desktop extensions. Which to use when, the config format, and troubleshooting.
Notion MCP server: setup, tools, and how to keep an agent's writes under control
Notion runs an official hosted MCP server at mcp.notion.com with OAuth. This guide covers connecting it from Claude, Claude Code, Cursor and ChatGPT, what the tools do, the workflows worth automating, and how to control writes and prompt injection from page content.
RAG vs MCP vs API: what each one solves and when to use which
RAG, MCP and plain APIs are often compared as if they compete. They solve different problems: RAG finds the right text, an API is a contract between programs, MCP lets a model discover and call tools. This guide explains each, when to pick which, and how they combine in an MCP server that exposes retrieval.
Gong MCP server: what it exposes, how to connect Claude, and what it costs
Gong runs an official, read-only MCP server at mcp.gong.io with three tools: ask_account, ask_deal and generate_brief. This guide covers what it returns (and what it does not), the admin setup, connecting Claude, ChatGPT and Claude Code, credit consumption, and when Fireflies or Fathom fit better.
Stripe MCP server: setup, agent keys, and safe access for finance teams
Stripe runs an official remote MCP server at mcp.stripe.com. This guide covers connecting it from Claude, Claude Code and Cursor, OAuth versus agent API keys, the tools it exposes, the questions finance teams can ask, and how sandboxes, read-only permissions and approval rules keep an agent away from your money.
Playwright MCP: setup in Claude Code, Cursor and VS Code, flags, and safe use
Microsoft's Playwright MCP server (@playwright/mcp) lets an AI agent drive a real browser through accessibility snapshots. How to install it in Claude Code, Cursor, VS Code and Claude Desktop, the flags that matter, when to use Chrome DevTools MCP instead, and how to keep sessions and cookies safe.
Datadog MCP server: setup per site, tools, and safe on-call use
Datadog runs an official remote MCP server with an endpoint per Datadog site, including EU1 at mcp.datadoghq.eu. This guide covers setup in Claude Code and Cursor, OAuth and key auth, toolsets, incident workflows, rate limits, and how to keep write tools under control.
Atlassian MCP server: connect Jira and Confluence to Claude, Cursor and ChatGPT
Atlassian's official Rovo MCP server gives AI clients governed access to Jira, Confluence and more at mcp.atlassian.com/v2/mcp. Setup per client, OAuth vs API tokens, the tools it exposes, admin controls, Rovo credits and how to keep writes in check.
Linear MCP server: setup, auth options and safe write access
Linear hosts an official remote MCP server at mcp.linear.app. This guide covers OAuth and API key auth, the read-only endpoint, setup in Claude, Claude Code, Cursor, VS Code and Codex, what the tools cover, and how to keep an agent's writes to your issue tracker under control.
GitHub MCP server: remote or local setup, toolsets, and safe defaults
How to set up GitHub's official MCP server (github/github-mcp-server) in Claude Code, Cursor and VS Code: the remote endpoint at api.githubcopilot.com, the local Docker image, OAuth vs PAT, toolsets, read-only and lockdown mode, GitHub Enterprise, and the prompt injection risk in issue text.
Klarna MCP server: connect Claude to Klarna orders, payouts and disputes
klarna-mcp is an open-source MCP server for Klarna's merchant APIs, built by Walma. It reads orders, captures, payouts, settlement transactions and disputes, is read-only by default, and keeps captures and refunds behind an explicit flag. Setup for Claude Code, Claude Desktop and Cursor.
Snowflake MCP server: setup, tools, RBAC and cost
Snowflake's managed MCP server runs inside your own Snowflake account and exposes Cortex Agents, Cortex Analyst, Cortex Search and read-only SQL to Claude, Cursor and other MCP clients. This guide covers the CREATE MCP SERVER spec, the grants, OAuth setup for Claude, limits and what it costs.
Asana MCP server: connect Asana to Claude, Claude Code and Cursor
Asana runs an official hosted MCP server (V2, generally available) at mcp.asana.com/v2/mcp. This guide covers OAuth app registration, setup in Claude, Claude Code and Cursor, the full tool list with read and write tools, admin controls and the limits worth knowing.
Sentry MCP server: setup, tools and scoping for Claude Code and Cursor
Sentry's official MCP server runs hosted at mcp.sentry.dev with OAuth, or locally via npx for self-hosted Sentry. This guide covers setup in Claude Code, Cursor and VS Code, project scoping, the tool list, how to limit it with skills, Seer, and safe use on error data.
Grafana MCP server: Cloud vs open source, setup and read-only mode
Grafana Labs ships two official MCP servers: a hosted Grafana Cloud MCP at mcp.grafana.com (public preview) and the open-source mcp-grafana for any Grafana 9+. This guide covers which to choose, setup in Claude Code and Claude Desktop, service account tokens, the tools, and how to run it read-only.
PostHog MCP server: setup, EU region, read-only mode and tools
PostHog's official MCP server is hosted at mcp.posthog.com with an EU endpoint at mcp-eu.posthog.com. This guide covers the setup wizard and Claude Code, OAuth vs personal API keys, read-only mode, limiting tools with features and project pinning, and what it costs.
LinkedIn Ads MCP server: give Claude your Campaign Manager data
linkedin-ads-mcp is an open-source MCP server for LinkedIn Campaign Manager, built by Walma. It reads accounts, campaigns, ads, performance and audience demographics, and can build campaigns as drafts that a person launches. How to get Advertising API access, set it up for Claude Code, Claude Desktop and Cursor, and what to ask it.
Agent skills
Reusable instruction packages that make an agent good at a specific task. How they work, how to build your own, and how they differ from MCP.
Claude skills: how to install and write skills for Claude Code and Claude.ai
Agent skills are folders with a SKILL.md file that teach Claude how to do a specific task. Here is how they work in Claude Code, Claude.ai and the API, where to find good ones, how to build your own, and what to watch for before rolling them out to a team.
Read the guide →Claude skills vs MCP: what each one does and when to use which
Skills teach an agent how to do a task. MCP gives it access to tools and data. They are not competitors. Here is a clear comparison, the questions that decide which you need, and how they work together in a real workflow.
Anthropic skills: the official GitHub repo, the document skills and which ones to install
A practical guide to Anthropic's official skills: what is in the anthropics/skills GitHub repository, how the docx, xlsx, pptx and pdf document skills work, how to install them in Claude Code through the plugin marketplace and use them in Claude.ai and the API, which ones are worth your time, and what the licences allow.
The best Claude skills in 2026: official, community and how to pick
A curated list of the best Claude skills for Claude Code and Claude.ai: Anthropic's official skills, the most-used community skills (humanizer, stop-slop, grill-me, taste, superpowers), marketing collections, and how to install and vet each one.
Claude skill creator: build and test your own skills with skill-creator
skill-creator is Anthropic's official skill for building Claude skills. This guide covers how to install it in Claude Code and Claude.ai, its workflow from interview to evals, benchmarks against a baseline, description optimisation, and packaging a skill for your team.
Claude marketing skills: the best collections and how to use them with real data
The best Claude skills for marketing: coreyhaines31/marketingskills and the alternatives, what each covers (copywriting, CRO, SEO, ads, email, launch), how to install them in Claude Code and Claude.ai, and how to combine them with live data from Google Ads, GA4 and Search Console through MCP.
Claude Code
Anthropic's coding agent for the terminal. Installation, cost, security, and how to run it in an EU environment.
What is Claude Code? A complete guide to Anthropic's coding agent
Claude Code is Anthropic's agentic coding tool that runs in your terminal, reads your codebase, edits files, runs tests and opens pull requests. This guide covers what it does, how it compares with Cursor, Codex and Copilot, how to install it, what it costs, and how to run it in an EU environment with policy and logging.
Read the guide →How to install Claude Code on macOS, Linux and Windows
Step-by-step installation of Claude Code with the native installer or npm, first sign-in, project setup with CLAUDE.md, the VS Code and JetBrains integrations, common errors, and how to run it through an EU region or a gateway.
Is Claude Code free? Claude Code pricing and cost control explained
What Claude Code costs: the differences between Pro, Max, Team, Enterprise and API billing, what a usage allowance means in practice, how much a developer typically spends per month, and how to keep costs under control across a team.
Cursor vs Claude Code: which AI coding tool fits your team?
An honest comparison of Cursor and Claude Code as of October 2026: interface, models, agent capabilities, pricing tiers, MCP and skills support, team and enterprise controls, when to pick which, and how to run both side by side.
Claude Code vs Codex: an honest comparison for teams (2026)
Claude Code vs OpenAI Codex compared on what matters to a team: surfaces and workflow, models, pricing, sandboxing and approvals, MCP, skills and AGENTS.md vs CLAUDE.md, and enterprise data residency. Plus why many teams end up running both.
How to use Claude Code: a hands-on tutorial for daily work
A practical Claude Code tutorial for after installation: your first session, permission modes, plan mode, CLAUDE.md and /init, the slash commands that matter, context management, subagents, hooks, MCP and skills, plus a worked example from bug to tested pull request.
Claude API key: how to get one, use it and keep it safe
How to create a Claude API key in the Claude Console, which key type to choose (personal, service account or legacy workspace key), how to use it with curl and the SDKs, how expiration and workspaces work, and how a team should manage keys so one leak does not become a bill.
Claude API pricing: what each model costs and how to keep the bill down
Claude API pricing per model (Fable, Opus, Sonnet, Haiku), what prompt caching, batch processing, web search, code execution and Managed Agents add, worked cost examples, spend caps per tier, and the levers that actually reduce a company's Claude bill.
Prompts and prompt engineering
How to write instructions that get good answers, from the basics to reusable patterns for teams.
What is a prompt? How to write prompts that work at work
A prompt is the instruction you give an AI model. This guide explains what goes into a good one, the techniques that reliably improve answers, the mistakes that ruin them, and how teams move from ad-hoc prompts to reusable skills.
Read the guide →AI tools for business
Which tools companies actually use, what they cost, and what to think about before rolling them out.
The same tools, in your EU region, under your control
A 20-minute walkthrough with an engineer. We map it to your tools, your MCP servers and your budget model.