Kennmarq.com

com.kennmarq由 kennmarq.com 发布官方发布者v0.1.0更新于 Nov 4, 2026

Rules and code for marking AI images, video and audio with C2PA and watermarks

已验证Streamable HTTP可网页运行开发者工具媒体与设计

概览

AI 生成的概览

Kennmarq.com 的远程 MCP 服务器为编程助手提供 AI 标注法规要求、集成代码和文档,用于给 AI 生成的图像、视频和音频添加 C2PA 标记与水印。

可以做什么
  • 查询指定市场对 AI 生成图像、视频或音频文件的标注法规要求,以及标记调用必须发送哪些字段
  • 获取各技术栈(Vercel AI SDK、JavaScript、Python、ComfyUI、HTTP)的集成代码,包括需安装的包和服务端示例
  • 以 Markdown 形式读取 Kennmarq.com 的任意文档页面,或列出全部页面的索引
适用场景
当应用用 AI 生成或编辑图像、视频或音频,并希望助手为其加入不可见水印、签名的 C2PA 内容凭证,以及在法规要求处添加可见的 AI 标签时适用。它本身是规则与文档查询服务器,不直接执行标记。
运行要求
远程 Streamable HTTP 端点;这些工具读取公开信息,无需密钥或账号。真正执行标记需要 Kennmarq.com 账号,并在应用服务端以 KENNMARQ_API_KEY 设置 API 密钥。
安装前请注意
工具只返回规则、代码和文档;标记由应用调用 Kennmarq.com API 完成,KENNMARQ_API_KEY 必须仅保存在服务端。每月 1,000 次标记以内免费,法规说明仅供参考,不构成法律意见。

安装

在 SourceWeft 中

  1. 打开 控制台中的 Kennmarq.com,将其添加到工作区。
  2. 为需要使用其工具的对话启用该服务。

Web executable,通过 Streamable HTTP。 远程服务在工作区中配置后即可从网页运行时运行。

交给智能体安装

把这段提示词粘贴到 Claude Code、Codex、Cursor 等智能体,或 SourceWeft 对话中。智能体会读取该服务器的安装指南,先向你展示发布者、端点和登录方式,经你同意后再把它添加到你的客户端。密钥不会写进任何命令。

阅读 https://sourceweft.com/mcp/com.kennmarq%2Fkennmarq/install.md,并按其中说明把这个 MCP 服务器接入我的客户端。修改任何配置之前,先告诉我它的发布者、端点和登录方式,等我确认。不要把 API 密钥写进命令或我会提交的文件;问我密钥应从哪里获取。

查看智能体所依据的安装指南

其他 MCP 客户端

把它添加到你客户端的 mcpServers 配置中。

{
  "mcpServers": {
    "kennmarq-com": {
      "type": "http",
      "url": "https://api.kennmarq.com/mcp"
    }
  }
}

README

Kennmarq.com for coding agents

When an app generates or edits images, video or audio with AI, AI-labelling laws ask for machine-readable marks: the EU AI Act's Article 50 from 2 August 2026 (2 December 2026 for systems already on the market), California's AI Transparency Act, and others. This kit teaches coding agents to add Kennmarq.com (https://kennmarq.com) where an app makes AI media: an invisible watermark and signed C2PA Content Credentials in one call per file, plus the visible "AI" label where a law needs one. Free up to 1,000 marks a month.

It holds:

  • skills/kennmarq/: a skill in the Agent Skills format, with a reference for each stack (Vercel AI SDK, JavaScript, Python, ComfyUI, HTTP) and each market's rules;
  • rules/kennmarq.mdc: a Cursor rule that applies when AI media is in play;
  • snippets/AGENTS.md: a standing rule for a project that marks its AI files (paste it into AGENTS.md, or into CLAUDE.md for Claude Code, which reads AGENTS.md only when there's no CLAUDE.md);
  • the MCP server at https://api.kennmarq.com/mcp: each market's rules (get_requirements), the code for each stack (get_integration) and the docs (read_doc). It needs no key.

Install

Claude Code, as a plugin (the skill and the MCP server):

text
/plugin marketplace add Kennmarq-com/kennmarq-agent-kit/plugin install kennmarq@kennmarq

Any agent that reads skills (Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf and others):

bash
npx skills add Kennmarq-com/kennmarq-agent-kit

Codex: codex plugin marketplace add Kennmarq-com/kennmarq-agent-kit. Gemini CLI: gemini extensions install https://github.com/Kennmarq-com/kennmarq-agent-kit.

The MCP server alone, in Claude Code: claude mcp add --transport http kennmarq https://api.kennmarq.com/mcp; in Cursor: Add to Cursor; anywhere else, the URL https://api.kennmarq.com/mcp (Streamable HTTP).

Cursor rule: copy rules/kennmarq.mdc into your project's .cursor/rules/.

The API key

Apps call Kennmarq.com with a key in KENNMARQ_API_KEY, on the server. Ask the user to create a free account at https://kennmarq.com/signup (no card), confirm the email and create a key in the dashboard.

Docs: https://kennmarq.com/docs/guides/ai-coding-agents. MIT-licensed.

来源:README.md,提交 9932846

工具

3

get_requirements

AI-labelling rules for markets

What the AI-labelling laws of the given markets ask of an AI-generated image, video or audio file, and what a call to POST /v1/mark must send for them: the fields required, whether the visible label is needed, and what can't be marked yet. Answers from the rules the API itself enforces, with links to the government texts.

输入参数media必填markets必填deepfake

get_integration

Code to mark AI media, per stack

How to add Kennmarq.com marking to an app's code: the package to install, a server-side example that marks each generated file before it's stored or shown, the fields to send, the API key and how to check the result. Stacks: ai-sdk (Vercel AI SDK middleware), javascript (Node.js, Next.js, Bun, Deno, edge), python, comfyui, http (any other language).

输入参数stack必填

read_doc

Read a Kennmarq.com docs page

A Kennmarq.com documentation page as Markdown: the API reference, the guides, the SDKs and the laws pages. The index of every page, with one line each: https://kennmarq.com/llms.txt.

输入参数path必填

版本历史

1
  1. v0.1.0最新Nov 4, 2026

评分

已满足适用检查项的 100%

该评分衡量此收录条目的完整程度,依据注册中心条目、端点与公开来源计算得出。它不是对服务器本身的评价,也不表示服务器安全或当前可用:可连通性是带日期的检查结果,评分也不包含安装量或用户评价。

  • 近 30 天内可连通必需25 分
  • 已声明认证方式必需10 分
  • 已列出工具必需15 分
  • 描述必需15 分
  • 图标10 分
  • 文档15 分
  • 许可证10 分