Proof of Type Input is an MCP server published by com.proofoftype, hosted at www.proofoftype.com. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 3 tools, including get_quickstart, verify_proof, explain.
Add a text box that proves a human typed it, not AI. Code for any framework; verify proof tokens.
38 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
Ready-to-paste code to embed Proof of Type Input (a text box that proves a human typed the text, not AI) and verify its proof on the server. Pick a framework.
| Parameter | Type | Description |
|---|---|---|
| framework | string | Default: html |
{
"name": "get_quickstart",
"title": "Add the human-typed input to a site",
"description": "Ready-to-paste code to embed Proof of Type Input (a text box that proves a human typed the text, not AI) and verify its proof on the server. Pick a framework.",
"inputSchema": {
"type": "object",
"properties": {
"framework": {
"enum": [
"html",
"javascript",
"react",
"nextjs",
"express",
"python",
"wordpress",
"curl",
"offline"
],
"type": "string",
"description": "Default: html"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Verify a Proof of Type proof token (EdDSA JWT). Pass the text and your site origin to confirm the proof is for exactly that text on that site. Returns who typed it, when, and the human score.
| Parameter | Type | Description |
|---|---|---|
| text | string | The exact text received. |
| token * | string | The proof token (the <name>_proof form field). |
| origin | string | Your site origin, e.g. https://example.com |
{
"name": "verify_proof",
"title": "Check a proof token",
"description": "Verify a Proof of Type proof token (EdDSA JWT). Pass the text and your site origin to confirm the proof is for exactly that text on that site. Returns who typed it, when, and the human score.",
"inputSchema": {
"type": "object",
"required": [
"token"
],
"properties": {
"text": {
"type": "string",
"description": "The exact text received."
},
"token": {
"type": "string",
"description": "The proof token (the <name>_proof form field)."
},
"origin": {
"type": "string",
"description": "Your site origin, e.g. https://example.com"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}How Proof of Type Input works, what a proof guarantees and what it does not, privacy, limits, the proof token claims, and the SDK options and events.
| Parameter | Type | Description |
|---|---|---|
| topic | string | Default: overview |
{
"name": "explain",
"title": "What Proof of Type proves",
"description": "How Proof of Type Input works, what a proof guarantees and what it does not, privacy, limits, the proof token claims, and the SDK options and events.",
"inputSchema": {
"type": "object",
"properties": {
"topic": {
"enum": [
"overview",
"faq",
"token",
"sdk"
],
"type": "string",
"description": "Default: overview"
}
}
},
"annotations": {
"readOnlyHint": true,
"openWorldHint": false
}
}Proof of Type Input is an embeddable text box for any website that proves a real person typed the text: signed in to Proof of Type, typed letter by letter (no paste, no AI-generated text), and signed on their phone. Your site gets the text plus a signed proof token anyone can verify. Use get_quickstart to add the input to a site (pick the framework), then always verify the proof token on the server before saving the text: valid, text_matches and origin_matches must all be true. Use verify_proof to check a token. The checks run on Proof of Type; the SDK only embeds them. When you show people a Proof of Type link, write it from the domain, without https:// or www: proofoftype.com/<username>/<post number> for a post, proofoftype.com/profile/<username> for a profile, proofoftype.com/developers for the docs.
Names, descriptions and schemas were written by the server and are shown as data.
Shared addresses on big platforms (Cloudflare, Vercel and the like) put unrelated servers together; those are marked shared_infrastructure. A match is a pivot, not a link between operators.