What it is, how to implement it, how to verify it. Services AI agent readiness audit WebMCP Implementation Agentic SEO architecture Structured data and schemas API optimization and data layer for AI Knowledge graph and entity modeling WebMCP migration and refactoring WebMCP consulting for companies and agencies WebMCP for online stores Origin trial and technical compliance WebMCP maintenance and monitoring See all services Blog Leaderboard RO EN
41/ 100

reset-monorepo.vercel.app D

This site registers real WebMCP tools at runtime. There is significant room for improvement.

Scanned 3 weeks ago with Chrome 152, real execution with a modelContext interceptor and synthetic interaction.

Scan another site

Agent access8 / 22
PASS Page loads over HTTPS 8/8 pts
The page answered with HTTP 200 over HTTPS.
FAIL AI agents allowed in robots.txt 0/6 pts
robots.txt blocks: gptbot, claudebot, claude-web, anthropic-ai, perplexitybot, ccbot, google-extended, bytespider, meta-externalagent.
How to fix: Remove Disallow rules that target AI crawlers (GPTBot, ClaudeBot, PerplexityBot, Google-Extended and similar) or that block the whole site.
FAIL llms.txt present 0/4 pts
No usable llms.txt found.
How to fix: Publish /llms.txt: a plain-text overview of the site (purpose, key pages, tools, contact) that AI models can read cheaply.
FAIL Not blocked by noindex 0/4 pts
A noindex directive was found (meta robots or X-Robots-Tag header).
How to fix: Remove the noindex directive so agents and search engines may use the page.
WebMCP tools, measured in a real browser32 / 46
We load the page in Chrome, intercept modelContext before any script runs and record what your page actually registers.
PASS WebMCP tools detected at runtime 14/14 pts
13 tool(s) registered through modelContext.registerTool() while the page ran in our Chrome.
PART Tool schema quality 18/20 pts
Average schema quality 5.5/6 across 13 tool(s). Weakest: get_product (5/6), get_session_state (5/6), open_login (5/6), open_product (5/6).
How to fix: Give every tool a clear description, a JSON Schema with typed and described parameters, constraints (enum, minLength, pattern, format), additionalProperties: false, and readOnlyHint annotations where they apply.
FAIL Origin Trial token 0/12 pts
No origin-trial token found. While WebMCP is in origin trial, stable Chrome only exposes modelContext to origins that serve a valid token.
How to fix: Register your origin at developer.chrome.com/origintrials for the WebMCP trial and serve the token in a meta http-equiv="origin-trial" tag. Without it, stable Chrome does not expose modelContext to your visitors while the API is in trial.
Discovery, community conventions0 / 12
Not part of the official Chrome spec. Scored as a small bonus because static crawlers and directories use it.
FAIL Discovery manifest at /.well-known/webmcp 0/6 pts
No valid JSON at /.well-known/webmcp (status 404).
How to fix: Publish a JSON file at /.well-known/webmcp describing your tools. It is not part of the official spec, but it lets crawlers and static tools discover what your site offers.
FAIL Manifest describes tools 0/3 pts
The manifest does not describe any tools.
How to fix: Add a "tools" array with name, description and inputSchema for each tool.
FAIL Manifest served as application/json 0/3 pts
No manifest to evaluate.
How to fix: Serve the manifest with the Content-Type: application/json header.
Coverage, how much of the site the agent sees1 / 20
We open several inner pages and check whether the tools travel with the user through the site or sit only on the entry page.
PART Tools on more than the entry page 1/6 pts
Only 1 of 10 checked pages expose tools.
How to fix: Register tools across the site, not only on the landing page. An agent that arrives straight on an inner page, from a search or a link, has to find what it needs there.
FAIL The surface adapts to the page 0/14 pts
Every page exposes exactly the same tools, so nothing is tied to the current page.
How to fix: Add tools tied to the page the agent is on: the details of that product or service, that page form, search within the current section. The same tools everywhere is a header, not a capability.

Tools registered by this page

NameDescriptionParametersRead-only
search_products Search the storefront catalog by keyword. Returns product and variant identifiers, price,... 1 yes
get_product Get authoritative Commerce Engine product details, including variants, by product ID or st... 1 yes
browse_store List storefront categories, or list the products in one category. Returns storefront URLs. 1 yes
get_variant Resolve one product variant and return its canonical storefront URL. Does not navigate; us... 2 yes
get_session_state Check whether the shopper is signed in. Browsing and cart changes work while signed out; o... 0 yes
open_login Open the sign-in screen so the shopper can authenticate themselves. You cannot sign anyone... 0 no
open_product Navigate the shopper to a product or variant URL that was already resolved by get_product,... 1 no
get_cart Read the shopper's current cart: every line with its product and variant IDs, quantity, pr... 0 yes
add_to_cart Add one or more products to the shopper's cart. Batch every item for one request into a SI... 1 no
set_cart_item_quantity Set an existing cart line to an absolute PAID quantity, not a delta. Promotional free unit... 3 no
remove_from_cart Remove one line from the shopper's cart, identified by the exact productId and variantId r... 2 no
open_cart Open the cart drawer so the shopper can review its contents. Does not change the cart. 0 no
open_checkout Open checkout so the shopper can complete the purchase themselves. This does NOT place an... 0 no

Captured live from modelContext.registerTool() calls while the page ran. A static HTML scan cannot see these.

Not measurable remotely, so not scored: end-to-end tool execution by an agent, human-in-the-loop consent handling, and result quality. Test those with the Model Context Tool Inspector extension in a WebMCP-capable Chrome.

Push this score higher?

GOAI implements WebMCP end to end: imperative tools, valid schemas, the origin trial token and the discovery manifest.

See our services