MODULE 3.3 / 9 OF 9
WebMCP: Your Site Talking to Agents
Explain what changes when agents visit websites, what WebMCP is, and the first concrete step: assess your own site and fix the basics.
Area page: eventos.inema.pro/webmcp/en/ · in the menu: “sites that communicate with agents”
1What Is WebMCP
What it is
WebMCP is a way for a page to describe what it can do to AI agents. Without WebMCP, an agent has to find fields, click, type, and interpret the screen. That breaks when the layout changes. With WebMCP, the page exposes tools with a name, description, argument schema, and response, and the agent calls the right tool by name. There are two paths: a declarative tool, where an existing form gets a toolname and a description, and an imperative tool, where JavaScript registers capabilities with JSON Schema and handles state, errors, cancellation, and fallback. This is experimental technology, currently behind an Origin Trial in the browser, which means it is available for testing.
Why learn it
It is the difference between an agent guessing and a site telling it. The site gets to decide what is allowed, what needs confirmation, and what can be canceled.
Key concepts
operating pixels vs. interacting with capabilities; declarative tool; imperative tool; JSON Schema; Origin Trial
In practice
Without WebMCP, the agent types the course name, clicks the blue button, and "thinks it worked." With WebMCP, the site exposes verificar_vagas and iniciar_inscricao; the agent calls the first, confirms there is an opening, and the second requires human confirmation before completion.
✓ Do
Choose a form on your site and write a name and one-line description it could have as a tool.
✗ Avoid
Judging the area by its name: read the main idea on the page before deciding if it’s for you.
2The Next Visitor Is an Agent
What it is
The page lists six changes. On the visitor side: agents already use browsers to fill out forms and complete tasks; search has become asking an assistant, which creates the GEO and AEO challenge; and the standard is taking shape now. On the publisher side: a site stops being just a screen and gains a catalog of capabilities layered over the human journey; discoverability becomes a requirement, with robots.txt, sitemap.xml, llms.txt, JSON-LD, Open Graph, and a clear identity; and security stays with the site, not the model. GEO and AEO are practices for appearing in and being cited by AI assistant answers, not just search engines.
Why learn it
If you own the site, the last three changes are your to-do list. Those who understand the limitations early can learn at a lower cost.
Key concepts
agents in the browser; search has become asking; GEO and AEO; catalog of capabilities; discoverability; site security
In practice
A school notices that students ask an assistant "which agent course starts this month" instead of searching the site. The answer depends on what the model can extract from the school’s pages, and classic SEO alone does not solve it.
3Free Assessment: Readiness
What it is
WebMCP Readiness, at webmcp.inema.pro, opens the URL in a disposable browser, gathers observable signals, and turns the scan into a correction plan. It is a passive scanner: it checks robots.txt, sitemap.xml, and llms.txt and does not run any site tools. You get an overall score and four independent scores—WebMCP, SEO, GEO, and AEO—with evidence, alerts, blockers, up to 12 prioritized fixes, and recommended courses for each gap, in a JSON report. The scan examines only the URL you provide; it inventories the sitemap, but does not crawl its pages. The advanced scanners for each phase appear in the report as planned, not ready.
Why learn it
Starting with an assessment shows you where your site stands before you study. The page also makes the limitation clear: the scanner does not promise indexing, ranking, or citation by AI.
Key concepts
passive scanner; disposable browser; overall score + four scores; up to 12 fixes; JSON report; what requires human review
In practice
An agency scans a client’s contact page and sees the blocker "no llms.txt" at the top of the plan. It fixes the issue, scans again, and uses the two scores to show progress without promising a ranking.
Steps to try
- Open the area page beside this lesson.
- Run the scan at https://webmcp.inema.pro/ on your site’s main page and save the JSON report as your baseline.
- Write one sentence about what changed in your understanding.
4Eight Layers of a Ready Site
What it is
The page organizes the architecture into eight layers, in the order the training builds them. The first four describe the site: discovery (can the agent find the site?), tools (what can the site do?), contract (how do you call it and what comes back?), and state and errors (what happens when something goes wrong?). The last four protect the site: control (who confirms?), permissions (who can call?), backend and MCP (where does the truth live?), and evals and observability (is it really working?). The rule that applies across all layers: the LLM chooses the tool; the site decides whether it can run. The assessment already measures all of layer 1 and the observable signals from layers 2 and 5.
Why learn it
The layers show that exposing a tool is only the start. Without confirmation, permissions, and backend authorization, an agent can trigger something it should not.
Key concepts
discovery; tools; contract; state and errors; control; permissions; backend and MCP; evals
In practice
A store exposes an order lookup tool. The description says "lookup only," the backend checks whether the caller can view that order, and any change requires human confirmation. Logs later show whether the tool did what it said.
✓ Do
For your site, mark which of the eight layers you already cover and which layer question you would not know how to answer today.
✗ Avoid
Jumping to the tool or course without understanding the problem the area addresses.
5Six Fixes for This Week
What it is
Before any training phase, the page lists six fixes the site owner can make, each tied to an item the scanner checks. First, run the scan and record the scores as a baseline. Second, publish the three public files: robots.txt, an updated sitemap.xml, and an llms.txt that introduces the site to AI models. Third, fix the SEO basics the agent also reads: title, description, canonical, headings in order, image alt text, Open Graph, and JSON-LD. Fourth, write for people answering questions, with direct answers, definitions, lists, and tables. Fifth, show who is behind the site, with the organization, authorship, update date, and evidence. Sixth, choose a form that does not change anything risky as your first tool, such as a search or status check.
Why learn it
These fixes do not require you to program tools, and they already raise the scores. The page sums up the method: fix things, run the scan again, and watch the score rise.
Key concepts
baseline; robots.txt, sitemap.xml, llms.txt; basic SEO; AEO: direct answers; GEO: authorship and evidence; first safe tool
In practice
A self-employed consultant publishes llms.txt, adds update dates and authorship to articles, and creates an FAQ section with short answers. The following week, the scan’s GEO and AEO scores rise, with no new JavaScript written.
6The training and where to continue
What it is
WebMCP Training has an overview and four phases, all open and in Portuguese: Builder (build), Integrator (integrate), Agent Developer (orchestrate), and Expert (operate). Each phase has four modules with six topics each and uses JavaScript. If you do not code, start with the overview and diagnostic, then bring the phases to your team. Layers 1 and 2 are taught in Builder, 3 and 4 in Integrator, 5 and 6 in Agent Developer, and 7 and 8 in Expert. The page also points to AIV 2026 for AEO and GEO, the Computer Use with GPT-6 Astra course, and Super-Agentes, along with projects such as the Kit do Arquiteto de Agentes, INEMACCBOT, and os-agentes. The final invitation is direct: your own site is the best first module.
Why learn it
Knowing which phase teaches each layer lets you enter the training at the point that fits your role, instead of starting from scratch.
Key concepts
overview; Builder; Integrator; Agent Developer; Expert; four modules with six topics each; related courses
In practice
An online store owner completes the diagnostic and overview. The team’s developer starts with Builder to turn product search into a declarative tool, and saves permissions for when they reach Agent Developer.
Criteria for reviewing your worksheet
Use this rubric after the lab. Each row asks for evidence; marking a topic as read doesn’t mean the worksheet is complete.
| Criterion | Expected evidence | If it doesn’t meet the criterion |
|---|---|---|
| Main idea | You can describe the area in one sentence that reflects the page. | Reread the top of the page and topic 1. |
| Audience | You can say who the area is for and who it isn’t for. | Return to topic 2 and write an example from your work. |
| Core elements | You can name the area’s core elements. | Use the module diagram as a guide. |
| First step | You chose a small, concrete step. | Copy the first step recommended on the page itself. |
| Starting point | You know which course, kit, or project to open first. | Check topic 6 and the page’s access section. |
| Source | Every statement in the worksheet comes from the page. | Replace your assumptions with what the page says. |
HANDS-ON / ~10 MIN
Assess Your Site
Keep the area page open: https://eventos.inema.pro/webmcp/en/. Use an example from your work, without personal or client data.
Prompt: WebMCP Plan for My Site
Paste it into Claude, ChatGPT, or Codex. Replace the words inside < and > with details about your situation.
Read https://eventos.inema.pro/webmcp/.
I ran the assessment at https://webmcp.inema.pro/ for my site: <your site URL>.
Scan result (paste the JSON or the scores and blockers): <paste here>.
1. Explain each blocker in plain language and say which of the eight layers it belongs to.
2. Build this week’s list using the page’s six fixes, in the right order for my situation.
3. Suggest ONE first declarative tool based on a form of mine that does not change anything risky: name, description, and arguments.
4. Separate what the scanner can prove from what requires human review (backend authorization, idempotency, description vs. actual effect).
5. Indicate which phase of WebMCP Training I or my team should start with.
Do not promise ranking, indexing, or citation by AI.
Completion criterion
Explain what changes when agents visit websites, what WebMCP is, and the first concrete step: assess your own site and fix the basics. Keep the worksheet with the main idea, audience, first step, and starting point.
Open the area page ↗Review what you’ve learned
The scanner found a tool declared in a script on your site. Does that guarantee it is protected and works for every visitor?
View suggested answer
No. The scanner shows what is observable. Actual authorization in the backend, idempotency, whether the description matches the effect, and whether the definition is registered for every visitor require human review.
If your answer was different, return to the relevant topic and describe the difference in one sentence. This check won’t block your progress.
Module summary
- operating pixels vs. interacting with capabilities; declarative tool; imperative tool; JSON Schema; Origin Trial
- agents in the browser; search has become asking; GEO and AEO; catalog of capabilities; discoverability; site security
- passive scanner; disposable browser; overall score + four scores; up to 12 fixes; JSON report; what requires human review
- discovery; tools; contract; state and errors; control; permissions; backend and MCP; evals
- baseline; robots.txt, sitemap.xml, llms.txt; basic SEO; AEO: direct answers; GEO: authorship and evidence; first safe tool
- overview; Builder; Integrator; Agent Developer; Expert; four modules with six topics each; related courses
Check the source
Pages read on 28/09/2026. Area content changes; the official page takes precedence over this summary.