WEBMCP · MCP · AGENT-READY BUSINESS

Learn to build the agent-ready web.

Practical training for people who want to understand what is changing, build useful agent-facing tools, and put them to work in real websites and business workflows.

Understand it. Build it. Test it. Trust it.

Explore the courses ↓
WebMCP across everyday screens and connected experiences

WHAT WE TEACH

Not just how to connect a model.
How to get the job done.

WebMCP gives websites a structured way to expose actions to AI agents in the browser. MCP connects assistants to tools and services beyond the page. The opportunity is in understanding the boundary between them, designing useful tasks, and making the whole experience work safely.

Our programme combines technical foundations, practical implementation, business process design, accessibility, security, consent and operational proof. You do not need to be a developer to start. You do need to be curious about how work gets done.

THE COURSE PROGRAMME

Choose where you want to start.

Short, practical courses that build towards a working implementation. Course durations below are indicative and can be delivered as focused workshops or a structured programme.

01 · FoundationsAll levelsHalf day

WebMCP and the agent-ready web

Understand the shift from websites designed for people to browse towards websites that can expose structured actions to agents.

  • What WebMCP is, what MCP is, and how they differ.
  • How agents discover tools, understand inputs and invoke actions.
  • What the browser, website and connected service each control.
  • Current standards, browser experiments and implementation realities.
  • Where the business opportunities and limitations sit.

You leave with: a shared vocabulary, a system map and a shortlist of real tasks worth making agent-ready.

02 · Product and businessLeaders and product teamsHalf day

Designing agent-ready customer journeys

Start with the customer or employee outcome, not the technology. Find the friction and design a better task.

  • Map a journey from intent to verified outcome.
  • Identify actions, decisions, hand-offs and failure points.
  • Choose what belongs in the website, an MCP server or an existing API.
  • Design human approval points and useful recovery paths.
  • Prioritise opportunities by value, feasibility, risk and readiness.

You leave with: a prioritised agent-ready workflow blueprint and measurable acceptance criteria.

03 · Developer workshopDevelopers1 day

Build your first WebMCP tools

Move from the concept to a working browser-based implementation using a controlled example site.

  • Prepare a WebMCP-capable development environment.
  • Define tool names, descriptions, input schemas and outputs.
  • Register and expose website actions using the current supported API.
  • Discover and invoke tools from a compatible agent/browser setup.
  • Validate inputs, handle errors and keep actions within site rules.
  • Test the experience and document browser dependencies.

You leave with: a working read-only WebMCP example, source code and a repeatable test checklist.

04 · IntegrationDevelopers and architects1 day

WebMCP + MCP: connect the whole workflow

Understand how browser-facing actions connect to business systems without turning the website into an unrestricted integration layer.

  • Separate browser tools, MCP servers, APIs and system-of-record responsibilities.
  • Connect a website workflow to a controlled MCP service.
  • Map identity, session context and least-privilege access.
  • Handle asynchronous work, hand-offs and task continuity.
  • Design idempotency, timeouts, retries and failure recovery.

You leave with: a reference architecture and a working end-to-end integration pattern using safe example services.

05 · Trust and securitySecurity, risk and productHalf day

Consent, identity and safe agent actions

Capability is not permission. Learn how to make agent activity understandable, bounded and accountable.

  • Authentication versus authorisation, consent and delegated authority.
  • Read-only discovery versus actions that change the world.
  • Exact action scope, input validation and approval boundaries.
  • Protect credentials, personal data and sensitive outputs.
  • Record requests, approvals, execution receipts and verified outcomes.
  • Stop safely when the result is uncertain; never blindly replay consequential actions.

You leave with: a threat and permission model, an approval matrix and an evidence checklist.

06 · Quality and operationsDelivery teamsHalf day

Test, evaluate and operate agent-ready services

Prove that the task works. A successful demo or green unit test is not the same as a verified real-world outcome.

  • Test tool discovery, schemas, invocation and expected results.
  • Evaluate task completion, reliability and accessibility.
  • Test denial paths, expired sessions, timeouts and partial completion.
  • Separate simulated, browser-tested and production evidence.
  • Use receipts, telemetry and release checks to support operational confidence.

You leave with: an evaluation plan, acceptance suite and evidence-led release checklist.

WebMCP is an evolving browser capability. Practical exercises will clearly identify the browser/version and feature configuration used. Where WebMCP is unavailable, the underlying task remains usable through a conventional interface or documented fallback. No course promises universal browser support.

HOW THE LEARNING FITS TOGETHER

One practical progression.

Every course connects to the same end-to-end capability model.

Understand the task

Start with the person, their goal and the outcome that matters.

Design the tools

Define what the website or connected service should expose.

Build the connection

Implement WebMCP and MCP boundaries with real validation.

Secure and test

Prove permissions, failure handling, accessibility and recovery.

Verify the outcome

Capture evidence of what actually happened and improve it.

WHO IT IS FOR

Different roles. One shared understanding.

Business leaders and executives

Understand the opportunity, investment choices, customer impact, operating model and risks without needing to write code.

Product, design and service teams

Redesign customer and employee journeys around tasks, accessible interactions, clear permissions and measurable outcomes.

Developers and architects

Build browser tools, connect MCP services, integrate existing systems and test the implementation in a controlled environment.

Security, privacy and risk teams

Understand identity, consent, delegated authority, data handling, approvals, audit evidence and safe failure.

Educators and students

Explore how the web, browsers and AI agents are changing, then build and test small working examples.

Organisations and delivery teams

Work on a real business process with a cross-functional team and leave with a practical implementation plan.

THE PRACTICAL CAPSTONE

Bring one real task.
Make it work.

Each applied programme should finish with a task that can be demonstrated and tested. Examples include:

  • Search and compare products or services.
  • Check appointment or booking availability.
  • Prepare a quote, enquiry or service request.
  • Retrieve an order or application status.
  • Connect a website action to a controlled business workflow.

The evidence matters.

A capstone is assessed against tool discovery, correct inputs, expected outputs, permission boundaries, accessibility, error handling and recovery. Consequential actions remain protected by the service's real authorisation and approval rules.

Participants receive their working example, implementation notes and a record of what was tested. This is a course completion record, not an accredited industry certification.

LEARN FROM THE ECOSYSTEM

Our training. Open standards. Real tools.

We teach through our own structured curriculum and practical exercises, while keeping students connected to the source material and open-source ecosystem.

BRING YOUR PEOPLE. BRING A REAL TASK.

Learn it by doing it.

We are developing practical courses and organisation workshops for the emerging agent-ready web. Tell us what you want your people to understand or build.

Discuss training