Whycant

io.github.sattyamjjainPublished by GitHub account sattyamjjainv0.6.0Updated Oct 24, 2026

Roast any AI agent idea from your IDE: verdict tier, readiness score, top risk, shareable URL.

VerifiedStreamable HTTPWeb executableDeveloper ToolsSecurity & Monitoring

Overview

AI-generated overview

A remote MCP server that roasts AI agent ideas, returning a verdict tier, readiness score, top security risk and a shareable result page.

What you can do
Roast an AI agent idea and get a verdict tier, an agent-readiness score with band, the top OWASP-MCP security risk and a shareable result URL, minting a persistent result page each time. Fetch an already-minted verdict by result id or slug without new analysis. Read live public stats such as total ideas roasted, share told to ship and how many came in via MCP. Browse the public explore feed of existing roasts, with optional free-text query and sorting, to check whether an idea was already roasted.
When to use it
Useful when you want a quick, opinionated sanity check on an AI agent idea before building it, or when you want to look up an earlier verdict or see what others have submitted.
Requirements
A remote endpoint over streamable HTTP; no local package. A bearer token in the Authorization header is required and must be requested from the operator; machine access only, not a human signup. Network access to the service.
Before you install
The Authorization bearer token is a secret and must be supplied in the header. Each roast_idea call mints a real, persistent public result page with a shareable URL, so submitted idea text becomes publicly visible; the other tools are read-only.

Installation

In SourceWeft

  1. Open Whycant in the dashboard and add it to a workspace.
  2. Connect Authorization token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.sattyamjjain%2Fwhycant/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "whycant": {
      "type": "http",
      "url": "https://whycantwehaveanagentforthis.com/api/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

This repository has no README.

Tools

4

roast_idea

Roast an AI agent idea

Get the full whycantwehaveanagentforthis.com roast for an AI agent idea: the verdict tier, an agent-readiness score (0-100 + band), the top OWASP-MCP security risk, the "you're the X% who…" framing, and a shareable /result URL. Every call mints a real, persistent result page (its own OG share card) — so roasting from your IDE also publishes it. Anonymous (no token): 3/hour, 10/day. Add a token for higher limits.

Parametersidearequired

get_verdict

Look up an existing verdict

Fetch a verdict that was already minted, by its result id or slug. Read-only — no new analysis, no rate-limit cost. Returns the same structured verdict shape as roast_idea.

Parametersidrequired

get_stats

Public roast-corpus stats

Live public numbers for whycantwehaveanagentforthis.com: total ideas roasted, live results, % told to ship, % that already exist, roast battles, and how many roasts came in via MCP. Read-only, no rate-limit cost.

Takes no parameters.

browse_explore

Browse the public roast corpus

Page through existing public roasts (the /explore feed) with their shareable /result URLs. Optional free-text query and sort (newest | top | money). Read-only, no rate-limit cost — use it to see whether an idea was already roasted before minting a new one.

Parameterssortlimitquery

Version history

1
  1. v0.6.0LatestSep 16, 2026

Score

75% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listedRequired15 pts
  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts

    Declare a GitHub repository with a README, or serve resource_documentation in the OAuth protected-resource metadata.

  • License10 pts

    Declare a license in the repository or the registry entry.