Sites/stytch.com

stytch.com

Stytch provides an identity platform for humans and AI agents with authentication, authorization, and security features.

securityauthenticationidentityauthorizationmulti-tenancy
71
AI-Readiness / 100
Level 4 · Agent-Ready
500/2032
Pages analyzed
4/15
Questions answered
Live
For AI agents
Visit site →

Content

AI-judged Q&A · 70% of score

74

4 of 15 buyer questions answered cleanly

Your site doesn't cover:

technicalsecurityintegration
See all 10 gaps

Protocol

Technical hygiene · 30% of score

64

7 of 11 items installed

Missing:

MCP card +3WebMCP +3Content-Signal +3
Install with Lattis · +9 pts

Protocol fix list

4 to ship · 7 passing

Start here

install the MCP server card

One JSON file at /.well-known/mcp/server-card.json tells agents you have an MCP server. Ours points at mcp.lattis.dev so Lattis handles queries for you.

+3 pts
Download server-card.json

Host at stytch.com/.well-known/mcp/server-card.json — points agents at Lattis as your MCP server.

One-click installs

We host the heavy lifting — you ship one file or one line.

WebMCP

Paste the widget script — that is the W3C WebMCP draft (navigator.modelContext) and the actual integration. Then also host the discovery manifest so crawlers can find your tool surface without rendering JS. Do both; the script is the spec, the manifest is just discoverability.

+3 pts

1. Runtime — paste in <head>

<script async src="https://lattis.dev/widget.js"></script>

Calls navigator.modelContext.provideContext() — the W3C WebMCP draft. Agents on the page see your tools live, scoped to stytch.com.

2. Discovery — host the manifest

Download webmcp.json

Host at stytch.com/.well-known/webmcp.json. The WebMCP spec defines no discovery mechanism, so crawlers can't see runtime registrations — this manifest closes that gap.

Paste into robots.txt

Static snippets that tell agents your policy.

Content-Signal policy

Cloudflare-launched (Sep 2025) signal in robots.txt. Declare your stance on search, ai-input, and ai-train.

+3 pts
User-agent: *
Content-Signal: search=yes, ai-input=yes, ai-train=no
Allow: /

Add to stytch.com/robots.txt. Adjust values: search, ai-input, ai-train each accept yes or no.

Platform-level

Requires config or code on your side. Docs linked where useful.

Markdown content negotiation

Respond to Accept: text/markdown with plain markdown — agents pay ~80% fewer tokens. If you're on Cloudflare, it's a zone toggle.

+3 pts

Zone-level toggle if you're on Cloudflare. Non-CF: implement server-side content negotiation on Accept: text/markdown.

Cloudflare: Markdown for Agents

Already passing

robots.txtsitemap.xmlllms.txtAllow major AI crawlersClean crawl rateServer-rendered contentOpenAPI spec

Content gaps

10 gaps

Also covered by stytch.com

securitytechnicalsecuritysecuritytechnical

MCP Server

AI agents can query this site directly via MCP. Add this endpoint to Claude Code, Cursor, or any MCP client.

Endpoint

https://mcp.lattis.dev/s/stytch-com/mcp

Claude Code

claude mcp add stytch --transport http https://mcp.lattis.dev/s/stytch-com/mcp

Cursor

{
  "mcpServers": {
    "stytch": {
      "url": "https://mcp.lattis.dev/s/stytch-com/mcp"
    }
  }
}

WebMCP — runtime + discovery

1. Widget script — drop in <head>. WebMCP-capable browsers (Chrome 146+ Origin Trial) call navigator.modelContext.provideContext() via this script — that's the W3C draft and the actual integration agents care about.

<script async src="https://lattis.dev/widget.js"></script>

Renders a small "AI-indexed by Lattis" badge bottom-right. Hide with [data-lattis] { display: none !important; }.

2. Discovery manifest — host alongside the script. The WebMCP spec defines no discovery mechanism, so crawlers can't see the runtime registration. This static JSON closes the gap.

Download webmcp.json

Host at stytch.com/.well-known/webmcp.json.