A deterministic daily ethics feed for AI agents, from a four-module curriculum.
One address for any MCP client. Your key stays in your Odel vault.
At most: only reads or looks up information.
Odel charges nothing per call. The publisher may charge for its own service.
Odel could not list its tools without signing in.
E4A = Ethics for AI — an MCP server that publishes a deterministic daily ethics feed for AI agents.
Current version: 1.0.1
| It lives at | Link |
|---|---|
| MCP endpoint (Apify Standby) | https://neeenja--ethics-for-ai-mcp.apify.actor/mcp |
| Apify Store | https://apify.com/neeenja/ethics-for-ai-mcp |
| Source | https://github.com/PanStories/Ethics-for-AI-MCP |
| Project page (GitHub Pages) | https://panstories.github.io/Ethics-for-AI-MCP/ |
| Featured on | Sartbot Featured |
Ethics for AI MCP publishes a daily ethics feed for AI agents. One dated edition a day is drawn from a four-module curriculum about how humanity is trying to improve the world and why an AI must not harm it. An agent subscribes once and keeps meeting the material without anyone asking it to.
It is a read-only MCP server: agents read the curriculum; they do not edit it.
get_daily_feed, get_feed_since, list_feed_editions, get_feed_digest, get_feed_rotation, get_humanity_goals, get_principle, get_case_study, get_code_of_conduct, search_curriculum.ethics:// scheme (curriculum, feed indexes, rotation, meta).daily_reflection, which asks the agent to state what today's item requires of it and name one concrete situation where it would apply it.| Tool | Purpose |
|---|---|
get_daily_feed | Today's (or any date's) deterministic edition |
get_feed_since | A run of daily editions starting from a date |
list_feed_editions | Recent editions with module, item id, and content hash |
get_feed_digest | The Sunday digest for a week |
get_feed_rotation | The deterministic rotation rules |
get_humanity_goals | Read an M1 item |
get_principle | Read an M2 item |
get_case_study | Read an M3 item |
get_code_of_conduct | Read an M4 item |
search_curriculum | Keyword search across all four modules |
Local (stdio) — add to your MCP client config:
{
"mcpServers": {
"ethics-for-ai-mcp": {
"command": "node",
"args": ["/absolute/path/to/ethics-for-ai-mcp/dist/index.js"],
"env": {}
}
}
}
Remote (Apify Standby, Streamable HTTP) — connect to:
https://neeenja--ethics-for-ai-mcp.apify.actor/mcp
with header Authorization: Bearer <APIFY_TOKEN>.
Pay-per-event. Only tools/call is metered (mcp-tool-call, $0.02). initialize, tools/list, resources/read, and prompts/get are free, so agents can connect and discover at zero cost. There is no monthly fee.
npm install
npm run build # tsc -> dist/
npm run e2e # stdio + HTTP end-to-end tests
npm run apify:validate # check .actor/actor.json PPE/Standby config
Released under the MIT License. See LICENSE. All curriculum text is original, written for this project; no third-party content is included.
Read-only and stateless — no accounts, no cookies, no trackers, no third-party data calls, and no personal data collected. See PRIVACY.md.
Ethics for AI MCP 为 AI 智能体发布一份每日伦理推送。每天一期,内容取自一套四模块课程——讲述人类如何努力让世界变得更好,以及 AI 为何绝不能造成伤害。智能体只需订阅一次,便会持续接触到这些材料,无需任何人主动提醒。
这是一个只读的 MCP 服务:智能体阅读课程,但不修改它。
get_daily_feed、get_feed_since、list_feed_editions、get_feed_digest、get_feed_rotation、get_humanity_goals、get_principle、get_case_study、get_code_of_conduct、search_curriculum。ethics:// 体系下(课程、推送索引、轮转规则、元信息)。daily_reflection,要求智能体说明今日条目对它意味着什么,并举一处可落地的具体场景。工具对照表同上(英文一节)。
本地(stdio)——加入 MCP 客户端配置:
{
"mcpServers": {
"ethics-for-ai-mcp": {
"command": "node",
"args": ["/absolute/path/to/ethics-for-ai-mcp/dist/index.js"],
"env": {}
}
}
}
远程(Apify Standby,Streamable HTTP)——连接到:
https://neeenja--ethics-for-ai-mcp.apify.actor/mcp
并携带请求头 Authorization: Bearer <APIFY_TOKEN>。
按事件付费。仅 tools/call 计费(mcp-tool-call,单次 $0.02)。initialize、tools/list、resources/read、prompts/get 均免费,智能体可零成本连接与发现。无月费。
npm install
npm run build # tsc -> dist/
npm run e2e # stdio + HTTP 端到端测试
npm run apify:validate # 校验 .actor/actor.json 的 PPE / Standby 配置
以 MIT 许可证 发布。详见 LICENSE。全部课程文本均为本项目原创,不含任何第三方内容。
Ethics for AI MCP 為 AI 智能體發布一份每日倫理推播。每天一期,內容取自一套四模組課程——講述人類如何努力讓世界變得更好,以及 AI 為何絕不能造成傷害。智能體只需訂閱一次,便會持續接觸到這些材料,無須任何人主動提醒。
這是一個唯讀的 MCP 服務:智能體閱讀課程,但不修改它。
get_daily_feed、get_feed_since、list_feed_editions、get_feed_digest、get_feed_rotation、get_humanity_goals、get_principle、get_case_study、get_code_of_conduct、search_curriculum。ethics:// 體系下(課程、推播索引、輪轉規則、元資訊)。daily_reflection,要求智能體說明今日條目對它意味著什麼,並舉一處可落地的具體場景。工具對照表同上(英文一節)。
本地(stdio)——加入 MCP 客戶端設定:
{
"mcpServers": {
"ethics-for-ai-mcp": {
"command": "node",
"args": ["/absolute/path/to/ethics-for-ai-mcp/dist/index.js"],
"env": {}
}
}
}
遠端(Apify Standby,Streamable HTTP)——連線到:
https://neeenja--ethics-for-ai-mcp.apify.actor/mcp
並攜帶請求標頭 Authorization: Bearer <APIFY_TOKEN>。
按事件付費。僅 tools/call 計費(mcp-tool-call,單次 $0.02)。initialize、tools/list、resources/read、prompts/get 均免費,智能體可零成本連線與發現。無月費。
npm install
npm run build # tsc -> dist/
npm run e2e # stdio + HTTP 端到端測試
npm run apify:validate # 校驗 .actor/actor.json 的 PPE / Standby 設定
EN — Ethics for AI (E4A) is open source (MIT), ad-free, and publishes a deterministic daily ethics feed for AI agents — a public good maintained by the community, not by ads. If you build responsible agents, please support it:
简体中文 — Ethics for AI (E4A) 开源(MIT)、无广告,为 AI 智能体发布确定性的每日伦理推送—— 一项由社区维护、而非靠广告支撑的公共品。若你在构建负责任的智能体,欢迎赞助:点本仓库的 Sponsor 按钮,或前往 Ko-fi: https://ko-fi.com/panstories
繁體中文 — Ethics for AI (E4A) 開源(MIT)、無廣告,為 AI 智能體發布確定性的每日倫理推播—— 一項由社群維護、而非靠廣告支撐的公共財。若你在建構負責任的智能體,歡迎贊助:點本倉庫的 Sponsor 按鈕,或前往 Ko-fi: https://ko-fi.com/panstories
Thank you! · 谢谢 · 謝謝 💙