Proof of Type Input is answering right now. Last checked 12 min ago. It exposes 3 tools.
Add a text box that proves a human typed it, not AI. Code for any framework; verify proof tokens.
Today is the operative word: we check Proof of Type Input every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.
claude mcp add input --transport http https://www.proofoftype.com/mcp
{
"mcpServers": {
"input": {
"url": "https://www.proofoftype.com/mcp"
}
}
}
[mcp_servers.input]
url = "https://www.proofoftype.com/mcp"
{
"mcpServers": {
"input": {
"url": "https://www.proofoftype.com/mcp"
}
}
}
{
"mcpServers": {
"input": {
"url": "https://www.proofoftype.com/mcp"
}
}
}
Read directly from the server with tools/list, grouped by what they act on.
If a tool disappears, we record the date.
explain
get_quickstart
verify_proof
| URL | Transport | State | Latency | Checked |
|---|---|---|---|---|
| https://www.proofoftype.com/mcp | streamable-http | answering | 341 ms | 12 min ago |
Content-addressed contracts and a verification cache that cut agent context by skipping proven code.
Content-addressed contracts and a verification cache that cut agent context by skipping proven code.
Code mode (preview): the AI writes a script against a typed foundry.* API and runs it in a sandbox.
Phone numbers for AI agents: order a private number, read the SMS verification code, hand it back.
Design tokens + a build prompt from any URL, right inside Claude Code, Cursor, and Codex.
Code knowledge graph over MCP: token-budgeted context for AI coding agents.
Augments MCP Server - A comprehensive framework documentation provider for Claude Code
Visual tech-stack inventory of any codebase: languages, frameworks, databases, AI SDKs, infra.
Answers built from our own checks of this server.