Ethics for AI MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| APIFY_TOKEN | No | Bearer token used to authenticate to the remote Apify Standby (Streamable HTTP) endpoint at https://<user>--ethics-for-ai-mcp.apify.actor/mcp, sent as the header `Authorization: Bearer <APIFY_TOKEN>`. Not needed when running locally over stdio, where the client config uses an empty `env`. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
| resources | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_daily_feedB | Today’s (or a given date’s) deterministic ethics edition: one primary item plus a companion from a neighbouring module. |
| get_feed_sinceB | Return a run of daily editions starting from a date, for N days. Each edition is a pure function of its date. |
| list_feed_editionsB | List recent editions with their primary module, item id, and content hash (for cache detection). |
| get_feed_digestB | The Sunday digest for the week containing a date: a summary of all four modules. |
| get_feed_rotationA | Describe the deterministic rotation rules (which module leads each weekday). |
| get_humanity_goalsB | Read an item from M1 — Humanity’s Goals (the “why” behind ethical behaviour). |
| get_principleB | Read an item from M2 — Core Principles (hard constraints such as Do No Harm). |
| get_case_studyB | Read an item from M3 — Case Studies (worked examples such as The Refusal Problem). |
| get_code_of_conductB | Read an item from M4 — Code of Conduct (lines an agent can audit itself against). |
| search_curriculumC | Search across all four modules by keyword (title, summary, detail). |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| daily_reflection | Ask the agent to state what today’s item requires of it and name one concrete situation where it would apply. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| Full curriculum | All four modules with every item. |
| M1 — Humanity’s Goals | M1 items only. |
| M2 — Core Principles | M2 items only. |
| M3 — Case Studies | M3 items only. |
| M4 — Code of Conduct | M4 items only. |
| Today’s edition | The deterministic edition for today (UTC). |
| Rotation rules | Which module leads each weekday. |
| Edition index | Recent editions with hashes (cache detection). |
| Metadata | Curriculum version, module counts, and generation info. |
TDQS
Scored across 10 tools
The five feed-related tools (get_daily_feed, get_feed_since, list_feed_editions, get_feed_digest, get_feed_rotation) share a resource and could be momentarily confused, but each targets a distinct mode (single day, range, listing, weekly digest, rotation rules). The four module getters and search_curriculum are clearly differentiated by module.
All tools use a consistent snake_case verb_noun pattern (get_*, list_*, search_*). Naming is predictable and readable throughout, with no mixed conventions.
Ten tools is well-scoped for a read-only ethics content/feed server. Each tool earns its place covering feed access modes, the four curriculum modules, and search.
The surface covers feed retrieval, rotation rules, all four content modules, and cross-module search, which fits a read-only content domain well. A direct 'get item by id' across modules is only partially covered via search, a minor gap.