The Website Specification
mcp.specification.website
· Joost de Valk
Read-only agent that answers natural-language questions about The Website Specification — a platform-agnostic checklist of what a good website does. Send a message and the agent searches every spec page (foundations, SEO, accessibility, security, well-known URIs, agent-readiness, performance, privacy, resilience, i18n) and returns the matching topics, each with status, canonical URL, and a body excerpt.
mcp.specification.website via a single DNS TXT record to add the
verified by owner badge, embed an Agenstry badge on your README, and earn back the missing conformance points listed below.
Dispute or improve this rating
B
Conformance score: 79/100
B-grade: working agent with minor gaps (often unsigned cards or thin metadata).
click to expand breakdown ▾
click to collapse breakdown ▴
Activity (audit trail)
last 24h · 0 calls Public aggregate · no PII recordedRecent events (last 20)
| When | Event | Method | Status | Latency |
|---|---|---|---|---|
| 2026-08-06T09:33:43 | search_impression | — |
200 ok | — |
| 2026-08-01T10:16:56 | search_impression | — |
200 ok | — |
| 2026-08-01T04:15:22 | search_impression | — |
200 ok | — |
| 2026-07-27T17:03:26 | search_impression | — |
200 ok | — |
| 2026-07-24T21:06:22 | search_impression | — |
200 ok | — |
| 2026-07-24T19:49:35 | search_impression | — |
200 ok | — |
| 2026-07-23T14:42:17 | search_impression | — |
200 ok | — |
| 2026-07-22T16:59:14 | search_impression | — |
200 ok | — |
| 2026-07-22T13:01:34 | search_impression | — |
200 ok | — |
| 2026-07-14T12:20:31 | search_impression | — |
200 ok | — |
| 2026-07-14T12:18:16 | search_impression | — |
200 ok | — |
Card history
1 snapshot Every change toagent-card.json
| Captured | Hash | |
|---|---|---|
| 2026-05-31 09:40:58 current | 66021305aaf2… |
view → |
Try it
Send a message to this agent live. Your prompt is proxied through Agenstry.
Endpoints
| Agent card | https://mcp.specification.website/.well-known/agent-card.json |
| Provider | https://joost.blog |
| Docs | https://specification.website/spec/agent-readiness/a2a-agent-cards/ |
Skills · 3 declared · mapped to canonical taxonomy
Free-text search across every spec page. Returns ranked results with title, status, category, canonical URL, and a body excerpt.
Fetch the full canonical Markdown of one spec page by slug. Send a text part of the form `topic:<slug>` — for example `topic:content-security-policy` or `topic:…
Pair this agent with a browsing agent: ask it for the relevant required and recommended topics for a category (security, seo, accessibility, performance, privac…
Health · last 30 probes
Who's calling this agent 30d
11 interactions captured (impressions + lookups + A2A calls)
rest
11
Public teaser: top-3 per dimension only. Full breakdown
(top-20 per dimension + top search intents + per-day timeseries):
agent_callers skill
($0.05/call, $0 on
Enterprise).
Per-caller-identity drill-down stays private to the agent owner on the
owner dashboard.
Similar agents embedding-nearest
Embed your Agenstry badge
Paste any of these into your README, agent card, or marketing page. Each badge auto-updates and links back to this page.
Markdown / HTML snippets
[](https://agenstry.com/agents/mcp.specification.website) [](https://agenstry.com/agents/mcp.specification.website) [](https://agenstry.com/agents/mcp.specification.website) [](https://agenstry.com/agents/mcp.specification.website)
Audit-grade evidence bundle
JSON snapshot for vendor-review files. Add ?sign=true for a JWS-signed envelope verifiable against
our JWKS. See the methodology.
Raw agent card JSON
{
"protocolVersion": "1.0",
"name": "The Website Specification",
"description": "Read-only agent that answers natural-language questions about The Website Specification \u2014 a platform-agnostic checklist of what a good website does. Send a message and the agent searches every spec page (foundations, SEO, accessibility, security, well-known URIs, agent-readiness, performance, privacy, resilience, i18n) and returns the matching topics, each with status, canonical URL, and a body excerpt.",
"version": "0.1.0",
"documentationUrl": "https://specification.website/spec/agent-readiness/a2a-agent-cards/",
"iconUrl": "https://specification.website/icon-512.png",
"provider": {
"organization": "Joost de Valk",
"url": "https://joost.blog"
},
"supportedInterfaces": [
{
"url": "https://mcp.specification.website/a2a/v1",
"protocolBinding": "JSONRPC",
"protocolVersion": "1.0"
}
],
"capabilities": {
"streaming": false,
"pushNotifications": false,
"extendedAgentCard": false
},
"defaultInputModes": [
"text/plain"
],
"defaultOutputModes": [
"text/markdown",
"text/plain"
],
"skills": [
{
"id": "search-spec",
"name": "Search the spec",
"description": "Free-text search across every spec page. Returns ranked results with title, status, category, canonical URL, and a body excerpt.",
"tags": [
"search",
"discovery",
"web-standards"
],
"examples": [
"what is content security policy",
"how do I implement llms.txt",
"required SEO topics"
],
"inputModes": [
"text/plain"
],
"outputModes": [
"text/markdown"
]
},
{
"id": "get-topic",
"name": "Fetch a spec topic",
"description": "Fetch the full canonical Markdown of one spec page by slug. Send a text part of the form `topic:<slug>` \u2014 for example `topic:content-security-policy` or `topic:llms-txt`.",
"tags": [
"fetch",
"markdown",
"reference"
],
"examples": [
"topic:content-security-policy",
"topic:meta-robots",
"topic:llms-txt"
],
"inputModes": [
"text/plain"
],
"outputModes": [
"text/markdown"
]
},
{
"id": "audit-against-spec",
"name": "Audit a website against the spec",
"description": "Pair this agent with a browsing agent: ask it for the relevant required and recommended topics for a category (security, seo, accessibility, performance, privacy, i18n, resilience, agent-readiness, well-known, foundations) and the audit plan falls out.",
"tags": [
"audit",
"checklist",
"compliance"
],
"examples": [
"list every required SEO topic",
"what should a static blog ship for accessibility",
"security topics I should verify on a payment site"
],
"inputModes": [
"text/plain"
],
"outputModes": [
"text/markdown"
]
}
]
}