Tool tree
validate_websiteact
Starts a NEW WebMCP validation scan for a public website. Returns a JSON object with the report link; the scan itself finishes in about 30 seconds, so fetch the report afterwards with get_webmcp_report. Rate limited to a few scans per hour. Use this only when the site has never been scanned or the user explicitly wants fresh results; if a report already exists, get_webmcp_report is instant and does not consume the limit.
View tool JSON
{
"name": "validate_website",
"kind": "act",
"impl": "imperative",
"description": "Starts a NEW WebMCP validation scan for a public website. Returns a JSON object with the report link; the scan itself finishes in about 30 seconds, so fetch the report afterwards with get_webmcp_report. Rate limited to a few scans per hour. Use this only when the site has never been scanned or the user explicitly wants fresh results; if a report already exists, get_webmcp_report is instant and does not consume the limit.",
"inputSchema": {
"type": "object",
"properties": {
"url": {
"type": "string",
"description": "Public website URL or domain, e.g. example.com",
"minLength": 4,
"maxLength": 300,
"pattern": "^(https?://)?[a-zA-Z0-9][a-zA-Z0-9.-]*\\.[a-zA-Z]{2,}"
}
},
"required": [
"url"
],
"additionalProperties": false
},
"page": "/"
}get_webmcp_reportanswer
Returns the latest COMPLETED validation report for a website, without starting a new scan. Returns a JSON object with `website`, `url`, `score` (0 to 100), `grade` (a letter grade), `categories` with `access`, `tools` and `discovery`, each carrying `points` out of `max`, `checks`, an array where each entry has an `id` and a `status` of pass or fail, `tools_detected`, `report_url` and `scanned_at`. Reach for this first whenever someone asks how a site scores; call validate_website only if no report comes back.
View tool JSON
{
"name": "get_webmcp_report",
"kind": "answer",
"impl": "imperative",
"description": "Returns the latest COMPLETED validation report for a website, without starting a new scan. Returns a JSON object with `website`, `url`, `score` (0 to 100), `grade` (a letter grade), `categories` with `access`, `tools` and `discovery`, each carrying `points` out of `max`, `checks`, an array where each entry has an `id` and a `status` of pass or fail, `tools_detected`, `report_url` and `scanned_at`. Reach for this first whenever someone asks how a site scores; call validate_website only if no report comes back.",
"inputSchema": {
"type": "object",
"properties": {
"website": {
"type": "string",
"description": "Domain of the website, e.g. example.com",
"minLength": 4,
"maxLength": 190,
"pattern": "^[a-zA-Z0-9][a-zA-Z0-9.-]*\\.[a-zA-Z]{2,}$"
}
},
"required": [
"website"
],
"additionalProperties": false
},
"page": "/"
}get_servicesanswer
The authoritative list of WebMCP services offered on this site, not a search result. Returns a JSON array of about 16 entries; each has `name`, `summary`, `price_from` (the entry price), `url`, `slug` and `parent` (the parent service, when the entry is a sub-service). The `slug` is what request_quote expects in its `service` field. Use it when someone asks what is offered or what something costs.
View tool JSON
{
"name": "get_services",
"kind": "answer",
"impl": "imperative",
"description": "The authoritative list of WebMCP services offered on this site, not a search result. Returns a JSON array of about 16 entries; each has `name`, `summary`, `price_from` (the entry price), `url`, `slug` and `parent` (the parent service, when the entry is a sub-service). The `slug` is what request_quote expects in its `service` field. Use it when someone asks what is offered or what something costs.",
"inputSchema": {
"type": "object",
"properties": {},
"additionalProperties": false
},
"page": "/"
}request_quoteact
Sends a quote request for a WebMCP service. Returns a JSON confirmation that the request was recorded; a human replies by email within one business day. Pass the `service` slug from get_services when the user has picked one. This sends a real message to a business, so ask the user to confirm before calling it.
View tool JSON
{
"name": "request_quote",
"kind": "act",
"impl": "imperative",
"description": "Sends a quote request for a WebMCP service. Returns a JSON confirmation that the request was recorded; a human replies by email within one business day. Pass the `service` slug from get_services when the user has picked one. This sends a real message to a business, so ask the user to confirm before calling it.",
"inputSchema": {
"type": "object",
"properties": {
"name": {
"type": "string",
"description": "Full name of the person requesting",
"minLength": 2,
"maxLength": 120
},
"email": {
"type": "string",
"description": "Email address for the reply",
"maxLength": 180
},
"phone": {
"type": "string",
"description": "Optional phone number",
"maxLength": 40
},
"company": {
"type": "string",
"description": "Optional company name",
"maxLength": 150
},
"website": {
"type": "string",
"description": "Optional website the request is about",
"maxLength": 255
},
"service": {
"type": "string",
"description": "Optional service slug from get_services, e.g. implementare-webmcp",
"maxLength": 190
},
"message": {
"type": "string",
"description": "What the user wants to achieve",
"maxLength": 4000
}
},
"required": [
"name",
"email"
],
"additionalProperties": false
},
"page": "/"
}get_leaderboardanswer
Returns the highest scoring websites validated on this site. Returns a JSON array where each entry has `website`, `score` (0 to 100), `grade` and `report_url`. Ordered best first; `limit` controls how many come back, between 1 and 25, defaulting to 10. Use it for questions about which sites are ready for AI agents, or to show an example of a good implementation.
View tool JSON
{
"name": "get_leaderboard",
"kind": "answer",
"impl": "imperative",
"description": "Returns the highest scoring websites validated on this site. Returns a JSON array where each entry has `website`, `score` (0 to 100), `grade` and `report_url`. Ordered best first; `limit` controls how many come back, between 1 and 25, defaulting to 10. Use it for questions about which sites are ready for AI agents, or to show an example of a good implementation.",
"inputSchema": {
"type": "object",
"properties": {
"limit": {
"type": "integer",
"description": "How many entries to return, between 1 and 25",
"minimum": 1,
"maximum": 25
}
},
"additionalProperties": false
},
"page": "/"
}scan_websiteact
Run a free WebMCP readiness scan for a public website and open the resulting report page. Prefer the validate_website tool if you want the result as JSON instead of a page.
View tool JSON
{
"name": "scan_website",
"kind": "act",
"impl": "declarative",
"description": "Run a free WebMCP readiness scan for a public website and open the resulting report page. Prefer the validate_website tool if you want the result as JSON instead of a page.",
"inputSchema": {
"type": "object",
"properties": {
"_token": {
"type": "string"
},
"url": {
"type": "string",
"description": "site-ul-dumneavoastra.ro"
}
},
"required": [
"url"
]
},
"page": "/"
}