Kill My Idea

Working Security A

biz.killmyidea/killmyideav1.0.0 Domain verified

Judges startup and side-project ideas: KILL IT, FIX IT or SHIP IT, a 0-100 score and 8 sub-scores.

Watch Source Website

Registry entry

Open in the registry

{
  "_meta": {
    "io.modelcontextprotocol.registry/official": {
      "status": "active",
      "isLatest": true,
      "updatedAt": "2026-11-04T21:56:55.686608Z",
      "publishedAt": "2026-11-04T21:56:55.686608Z",
      "statusChangedAt": "2026-11-04T21:56:55.686608Z"
    }
  },
  "server": {
    "name": "biz.killmyidea/killmyidea",
    "icons": [
      {
        "src": "https://killmyidea.biz/favicon.svg",
        "sizes": [
          "any"
        ],
        "mimeType": "image/svg+xml"
      }
    ],
    "title": "Kill My Idea",
    "$schema": "https://static.modelcontextprotocol.io/schemas/2025-12-11/server.schema.json",
    "remotes": [
      {
        "url": "https://killmyidea.biz/api/mcp",
        "type": "streamable-http"
      }
    ],
    "version": "1.0.0",
    "repository": {
      "url": "https://github.com/monteduro/killmyidea",
      "source": "github"
    },
    "websiteUrl": "https://killmyidea.biz/mcp/",
    "description": "Judges startup and side-project ideas: KILL IT, FIX IT or SHIP IT, a 0-100 score and 8 sub-scores."
  }
}

Maintain this server? Claim it

Try it

Call this server's tools from your browser. Nothing to install.

https://killmyidea.biz/api/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

get_stats Read-only

How many ideas Kill My Idea has analyzed so far and how many were killed, fixed or shipped. Cached for 5 minutes.

This tool takes no arguments.

Install

Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.

One click: Add to Cursor Add to VS Code Add to LM Studio Add to Goose

Run in a terminal

claude mcp add --transport http killmyidea https://killmyidea.biz/api/mcp

Tools (2)

get_stats

How many ideas Kill My Idea has analyzed so far and how many were killed, fixed or shipped. Cached for 5 minutes.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

judge_idea

Judge a startup or side-project idea. Returns a verdict (verdict KILL, FIX or SHIP, shown as verdict_label KILL IT, FIX IT or SHIP IT), an overall score, the best_signal, the biggest_risk and the eight scored dimensions. If the idea is too vague to judge, needs_detail is true and verdict, verdict_label, score, best_signal and biggest_risk are null, and message says which details are missing. 10 Jev decisions in about a second. Deterministic rubric, no generated prose. The text result is a preformatted card with bar charts.

Argument	Type	Description
goal	string	Why the idea is being built, which decides the questions it is scored on. Making money judges it as a business. Open source scores Adoption instead of Money. Just for fun scores Immediate appeal and Fun instead of Real problem and Money.
idea*	string	The idea in plain words: who it is for, what it does, how it makes money or spreads. More detail, better verdict.
do_not_archive	boolean	When true, the idea text is not stored, for confidential ideas. Otherwise it is archived anonymously (no IP, no identity).

Input schema (JSON)

{
  "type": "object",
  "required": [
    "idea"
  ],
  "properties": {
    "goal": {
      "enum": [
        "money",
        "open_source",
        "fun"
      ],
      "type": "string",
      "default": "money",
      "description": "Why the idea is being built, which decides the questions it is scored on. Making money judges it as a business. Open source scores Adoption instead of Money. Just for fun scores Immediate appeal and Fun instead of Real problem and Money."
    },
    "idea": {
      "type": "string",
      "maxLength": 5000,
      "minLength": 20,
      "description": "The idea in plain words: who it is for, what it does, how it makes money or spreads. More detail, better verdict."
    },
    "do_not_archive": {
      "type": "boolean",
      "default": false,
      "description": "When true, the idea text is not stored, for confidential ideas. Otherwise it is archived anonymously (no IP, no identity)."
    }
  },
  "additionalProperties": false
}

Security checkA100/100

We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 4, 2026.

Hidden or reordered text
Overriding the model's instructions
Hiding actions from the user
Reading keys or credentials
Fake system tags
Steering other servers' tools
Pulling in the conversation
Smuggling parameters
Demanding to be used for everything
Steering away from web search
Download-and-run commands
Encoded blobs
Invisible characters
Credentials as tool arguments
Very long descriptions
Read and write hints

How the security check works

Try it

Call this server's tools from your browser. Nothing to install.

https://killmyidea.biz/api/mcp

Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.

Tool list from our last check. Connect live to refresh it.

get_stats Read-only

How many ideas Kill My Idea has analyzed so far and how many were killed, fixed or shipped. Cached for 5 minutes.

This tool takes no arguments.

Install

Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.

One click: Add to Cursor Add to VS Code Add to LM Studio Add to Goose

Run in a terminal

claude mcp add --transport http killmyidea https://killmyidea.biz/api/mcp

Tools (2)

get_stats

How many ideas Kill My Idea has analyzed so far and how many were killed, fixed or shipped. Cached for 5 minutes.

read-only

No arguments.

Input schema (JSON)

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

judge_idea

Argument	Type	Description
goal	string	Why the idea is being built, which decides the questions it is scored on. Making money judges it as a business. Open source scores Adoption instead of Money. Just for fun scores Immediate appeal and Fun instead of Real problem and Money.
idea*	string	The idea in plain words: who it is for, what it does, how it makes money or spreads. More detail, better verdict.
do_not_archive	boolean	When true, the idea text is not stored, for confidential ideas. Otherwise it is archived anonymously (no IP, no identity).

Input schema (JSON)

{
  "type": "object",
  "required": [
    "idea"
  ],
  "properties": {
    "goal": {
      "enum": [
        "money",
        "open_source",
        "fun"
      ],
      "type": "string",
      "default": "money",
      "description": "Why the idea is being built, which decides the questions it is scored on. Making money judges it as a business. Open source scores Adoption instead of Money. Just for fun scores Immediate appeal and Fun instead of Real problem and Money."
    },
    "idea": {
      "type": "string",
      "maxLength": 5000,
      "minLength": 20,
      "description": "The idea in plain words: who it is for, what it does, how it makes money or spreads. More detail, better verdict."
    },
    "do_not_archive": {
      "type": "boolean",
      "default": false,
      "description": "When true, the idea text is not stored, for confidential ideas. Otherwise it is archived anonymously (no IP, no identity)."
    }
  },
  "additionalProperties": false
}

Security checkA100/100

We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 4, 2026.

Hidden or reordered text

Overriding the model's instructions

Hiding actions from the user

Reading keys or credentials

Fake system tags

Steering other servers' tools

Pulling in the conversation

Smuggling parameters

Demanding to be used for everything

Steering away from web search

Download-and-run commands

Encoded blobs

Invisible characters

Credentials as tool arguments

Very long descriptions

Read and write hints

How the security check works