Canonsheet

dev.kanekyPublished by kaneky.devOfficial publisherv0.3.0Updated Oct 24, 2026

Consistent prompts for one human character across image and video models. Paid per call, x402.

VerifiedStreamable HTTPWeb executableMedia & Design

Overview

AI-generated overview

Canonsheet builds a consistent prompt set for one human character — canonical image prompt, negative prompts, video prompt and optional contact sheet — for use.

What you can do
Build a consistent prompt set for one human character: a canonical image prompt with every appearance fact labelled, negative prompts that stop traits like glasses or a cane from vanishing, a video prompt, and optionally a contact sheet that holds everything fixed and walks one axis.
When to use it
Useful when you need repeatable, consistent prompts for the same human character across image and video models, and want negative prompts that keep specific traits from disappearing.
Requirements
Remote endpoint at canonsheet.kaneky.dev over streamable HTTP; no authentication, environment variables or headers are declared.
Before you install
Paid per call via x402, so using the tool spends money. The prompt content you submit is sent to a third-party remote service.

Installation

In SourceWeft

  1. Open Canonsheet in the dashboard and add it to a workspace.
  2. 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/dev.kaneky%2Fcanonsheet/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": {
    "canonsheet": {
      "type": "http",
      "url": "https://canonsheet.kaneky.dev/mcp"
    }
  }
}

Tools

1

build_character_prompts

Build a consistent prompt set for one human character: a canonical image prompt with every appearance fact labelled, negative prompts that stop traits like glasses or a cane from vanishing, a video prompt, and optionally a contact sheet that holds everything fixed and walks one axis. Works with any image or video model. Text keeps wardrobe and framing stable; for the same FACE across images, generate the canonical frame once and pass it back as a reference image (has_reference). Paid per call over x402: the first attempt answers HTTP 402 with the price. Invalid arguments are refused before any payment.

Parametersnamevideotraitschoiceswalk_axisappearancecustom_traitshas_reference

Version history

2
  1. v0.3.0LatestOct 18, 2026
  2. v0.2.4Sep 24, 2026

Score

72% 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

    Publish an icon in the registry entry.

  • Documentation15 pts

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

  • LicenseNot applicable

    A hosted service is used under its provider's terms, so no license is expected here. This check is left out of the percentage.

Other Kaneky integrations