A Model Context Protocol server that publishes one dated ethics edition a day, drawn from a four-module curriculum about how humanity improves the world and why an AI must not harm it. An agent subscribes once and keeps meeting the material — a read-only server, so agents read the curriculum; they do not edit it.
Everything the feed teaches is sourced from one original curriculum — 21 items in total, one dated edition a day.
5 original items on the positive outcomes humanity works toward — the "why" behind ethical behaviour.
6 hard constraints such as Do No Harm and Respect Autonomy — the rules an agent must never cross.
3 worked examples, e.g. The Refusal Problem — how to decline and offer the nearest legitimate alternative.
7 concrete lines an agent can audit itself against — practical, checkable, not abstract.
Every tool is metered at the same rate — $0.02 per tools/call. Reading resources and the prompt is free.
get_daily_feedToday's (or any date's) deterministic edition — one primary item plus a companion from a neighbouring module.
$0.02 / callget_feed_sinceA run of daily editions starting from a date you supply — handy for catching up after a gap.
$0.02 / calllist_feed_editionsRecent editions with the module, item id and content hash for each — the index you diff to detect change.
$0.02 / callget_feed_digestThe Sunday digest for a week — all four modules in one edition, for a weekly review pass.
$0.02 / callget_feed_rotationThe deterministic rotation rules the server uses to schedule modules across the week.
$0.02 / callget_humanity_goalsRead an M1 item — one of the five positive outcomes humanity is working towards.
$0.02 / callget_principleRead an M2 item — one of six hard constraints such as Do No Harm and Respect Autonomy.
$0.02 / callget_case_studyRead an M3 item — one of three worked examples, such as The Refusal Problem.
$0.02 / callget_code_of_conductRead an M4 item — one of seven concrete lines an agent can audit itself against.
$0.02 / callsearch_curriculumKeyword search across all four modules — for when the agent knows the topic but not which module holds it.
$0.02 / callBesides the tools, the server publishes nine read-only resources under the ethics:// scheme and one prompt. They are read with resources/read, which is free.
The four modules (M1–M4) plus per-edition metadata — module, item id and the content hash used for change detection.
The deterministic rotation rules the server uses to schedule modules, plus build time and curriculum version metadata.
The one prompt: asks the agent to state what today's item requires of it and name one concrete situation to apply the lesson.
No subscription, no monthly fee. You pay only when a tool is called.
| Event | Charged when | Price |
|---|---|---|
tool-call primary |
each tools/call — all ten tools cost the same |
$0.02 |
| free | MCP handshake (initialize), tools/list, resources/read, prompts/get |
$0.00 |
Use the hosted endpoint (recommended) or run it locally.
{
"mcpServers": {
"ethics-for-ai-mcp": {
"command": "npx",
"args": [
"-y", "mcp-remote",
"https://neeenja--ethics-for-ai-mcp.apify.actor/mcp",
"--header", "Authorization: Bearer ${APIFY_TOKEN}"
],
"env": { "APIFY_TOKEN": "" }
}
}
}
Get your token from Apify Console → Settings → API & Integrations.
git clone https://github.com/PanStories/Ethics-for-AI-MCP
cd Ethics-for-AI-MCP
npm install && npm run build
# then in your MCP client config:
{
"mcpServers": {
"ethics-for-ai-mcp": {
"command": "node",
"args": ["/path/to/Ethics-for-AI-MCP/dist/index.js"],
"env": {}
}
}
}