nope-mcp — Open Educational Resources search

Measured conclusion: Deep-tested. L2 outcome: tools_ok.

Search German open educational resources (OER) via AMB/schema.org metadata, open licenses only.

Add to your agent

Copy this into your MCP client config:

{
  "mcpServers": {
    "nope-mcp — Open Educational Resources search": {
      "url": "https://mcp.edufeed.org/mcp",
      "transport": "streamable-http"
    }
  }
}

Measured tools (18)

• search_resources read-only

  Search for educational resources (learning materials, courses, videos, etc.) using full-text search and metadata filters. Returns resources matching the query from the AMB relay. Only openly licensed resources are returned (CC0, Public Domain, CC BY, CC BY-SA); NC/ND, all-rights-reserved and unlicensed resources are left out. NOTE: the metadata filters (publisherName, creatorName, subjectLabel, resourceTypeLabel, educationalLevelLabel) are EXACT full-string matches against the stored metadata (case-insensitive) — not fuzzy or substring searches. A guessed spelling silently returns 0 results; use resolve_publisher to find the canonical actor spelling first. On a zero-match actor filter the response includes actorCandidates with similar spellings to retry with.

  Parameters:

  • limit — number — Maximum number of results (1-250, default: 20)
  • query — string — Free-text search query (e.g., "mathematik", "machine learning")
  • since — number — Return resources created at or after this Unix timestamp
  • until — number — Return resources created at or before this Unix timestamp
  • relays — array — Restrict the search to specific relays. Only relays returned by list_relays (default or extra) are accepted, by full URL or short name (e.g. "oersi", "sodix"). Default: the default relay set.
  • authors — array — Filter by author pubkeys (hex format)
  • language — string — Language for label filters (default: "de")
  • creatorName — string — Filter by creator/author name — EXACT full-string match (case-insensitive) against the AMB metadata. Unsure of the spelling? Call resolve_publisher first.
  • subjectLabel — string — Filter by subject/topic label — EXACT label match (e.g., "Mathematik", "Physik"); browse_subjects lists valid labels
  • publisherName — string — Filter by publisher name — EXACT full-string match (case-insensitive) against the AMB metadata, e.g. "e-teaching.org" or "LEHRE LADEN" (not "Lehreladen"). Unsure of the spelling? Call resolve_publisher first.
  • resourceTypeLabel — string — Filter by resource type label — EXACT label match (e.g., "Video", "Kurs", "Arbeitsblatt"); browse_resource_types lists valid labels
  • educationalLevelLabel — string — Filter by educational level — EXACT label match (e.g., "Sekundarstufe I", "Hochschule"); browse_educational_levels lists valid labels

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• search_content read-only

  Topic search across ALL content types on the relay in one ranked call: educational resources (kind 30142), long-form articles/blogs (30023), wikis (30818), projects (30143), measures (30144), and NKBIP-01 publications (30040 indices + 30041 sections — scientific articles, books). Results are interleaved and ranked by semantic passage match, and each carries the matched passage ("snippet") when available — use it to answer the user, not just list links. Educational resources are returned only when openly licensed (CC0, Public Domain, CC BY, CC BY-SA); the other content types carry no license and are all included. This is the tool for DISCOVERY intent — the user wants materials to browse ("finde/suche/empfiehl Materialien zu X"): present the items. For QUESTION intent — the user wants an answer built from the content ("wie/warum/was hilft bei X?") — prefer search_passages, which returns quotable fulltext passages with citations; this tool then supplements the answer with browsable links. Each result carries eventAuthor (the Nostr signer who uploaded the event — often an aggregator) plus, for resources, creator/publisher (who actually made and published the resource); these can differ, so do not treat eventAuthor as the publisher. For full metadata (license, dates, complete entity lists) pass a result's naddr to get_resource. Publication facets ride inside the query string as NIP-50 field filters: append type:academic, doi:10.1234/abcd.5678, keywords:<term>, or partOf:30143:<pubkey>:<d> ("publications of a project") to the query — the relay resolves them server-side. When presenting results to the user, render each as a markdown link so they can open it directly — prefer sourcePage (the original external source page, present on most resources and on projects/measures/publications), then url, then naddr. For upcoming events on the same topic, follow up with search_calendar_events.

  Parameters:

  • limit — number — Max results (1-250, default 20).
  • query — string — Free-text topic (e.g., "Unaufmerksamkeit im Seminar"). Keep it to the TOPIC only — do not append actor/organization names ("… Lehreladen"): they dilute the semantic ranking and the actor's content drops out of the top results. To constrain by actor, resolve the name first (resolve_author → authors param here; or resolve_publisher → search_resources publisherName).
  • since — number — Created at or after this Unix timestamp.
  • types — array — Restrict to a subset of content types. Default: all of them.
  • until — number — Created at or before this Unix timestamp.
  • relays — array — Restrict the search to specific relays. Only relays returned by list_relays (default or extra) are accepted, by full URL or short name (e.g. "oersi", "sodix"). Default: the default relay set.
  • authors — array — Filter by author pubkeys (hex).
  • language — string — Label language (default "de").
  • community — string — Return content shared into this community (Communikey). Accepts a hex pubkey or npub. Resolve a community name to its pubkey with resolve_author. Combine with query to scope a topic to a community (e.g. "math resources shared with X").

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• get_resource read-only

  Retrieve a single piece of content by naddr (preferred — pass a search_content result's naddr), d-tag identifier, or event ID. naddrs of ANY content type from search_content work (resources, articles, wikis, projects, measures, publications); non-resource kinds return the same shape as their search results. Bare identifier/eventId lookups (no naddr) always resolve the full educational-resource metadata (kind 30142), including creator/publisher and educational properties. Lookups are not license-filtered: a learning resource carries openLicense (true for CC0, Public Domain, CC BY, CC BY-SA — the open licenses that search results are currently limited to). When presenting the resource, render a markdown link the user can open: prefer its sourcePage (the original source page); fall back to url (the edufeed viewer) only when sourcePage is absent.

  Parameters:

  • naddr — string — NIP-19 naddr from a search result — the preferred handoff to fetch full metadata.
  • author — string — Author pubkey (hex) to disambiguate if multiple resources share the same identifier
  • relays — array — Restrict the lookup to specific relays — pass the relays a search found the result on. Only relays returned by list_relays (default or extra) are accepted, by full URL or short name (e.g. "oersi"). Default: the default relay set.
  • eventId — string — Nostr event ID (hex) for direct lookup. Alternative to identifier.
  • language — string — Preferred language for labels (default: "de")
  • identifier — string — Resource identifier (d-tag). Use this for stable lookups.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• browse_subjects read-only

  List available subjects/topics in the educational resource collection. Returns subjects with their labels and resource counts.

  Parameters:

  • limit — number — Maximum number of subjects to return
  • prefix — string — Filter subjects whose label starts with this prefix
  • language — string — Language for labels (default: "de")

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• browse_resource_types read-only

  List available learning resource types (Video, Course, Worksheet, etc.) with resource counts.

  Parameters:

  • limit — number — Maximum number of resource types to return
  • language — string — Language for labels (default: "de")

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• browse_educational_levels read-only

  List available educational levels (Primary, Secondary, Higher Education, etc.) with resource counts.

  Parameters:

  • limit — number — Maximum number of levels to return
  • language — string — Language for labels (default: "de")

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• relay_stats read-only

  Get information about all selectable AMB relays (default and extra), including supported NIPs, relay name, and description.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_relays read-only

  List the configured AMB relays. defaultRelays are searched on every query; extraRelays hold different corpora (e.g. the OERSI aggregation) and are only searched when a search/get tool call passes them in its relays parameter.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• relay_list_get read-only

  Get a user's NIP-65 relay list (kind 10002). Returns read and write relays for the specified pubkey. If no pubkey provided, uses the connected signer's pubkey.

  Parameters:

  • pubkey — string — Public key to fetch relay list for (defaults to connected signer)

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• skos_get_vocabulary read-only

  Fetch and parse a SKOS vocabulary from its URI. Returns the concept scheme with all concepts organized hierarchically.

  Parameters:

  • uri (required) — string — URI of the SKOS vocabulary (e.g., "https://w3id.org/kim/hcrt/scheme")
  • flat — boolean — If true, return a flat list of concepts instead of hierarchy. Default: false.
  • language — string — Preferred language for labels (e.g., "de", "en"). If not specified, all languages are returned.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• skos_get_concept read-only

  Get details of a single SKOS concept by its URI, including broader, narrower, and related concepts.

  Parameters:

  • uri (required) — string — URI of the concept (e.g., "https://w3id.org/kim/hcrt/video")
  • language — string — Preferred language for labels (e.g., "de", "en")

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• skos_search read-only

  Search for concepts in a SKOS vocabulary. By default searches prefLabel, altLabel, hiddenLabel, and definition.

  Parameters:

  • vocabularyUri (required) — string — URI of the vocabulary to search (e.g., "https://w3id.org/kim/hochschulfaechersystematik/scheme")
  • query (required) — string — Search query
  • limit — integer — Maximum number of results (default: 20, max: 100)
  • fields — array — Fields to search in. Default: ["prefLabel", "altLabel", "hiddenLabel", "definition"]
  • language — string — Limit search to this language (e.g., "de"). If not specified, searches all languages.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_known_authors read-only

  List known educational resource authors loaded from configured follow sets (NIP-51 kind 30000). Returns author names, pubkeys, and NIP-05 identifiers. Use the returned pubkeys with search_resources(authors: [...]) to filter resources by author.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• resolve_author read-only

  Resolve an org or person NAME to candidate pubkeys using the relay's kind-0 author-profile index (NIP-50 search). Use this to answer name-driven content questions like "recent articles and resources of Jörg Lohrer": call resolve_author(name), pick the best candidate, then pass its pubkey to search_content({ authors: [pubkey], ... }) (and/or search_calendar_events) to fetch that author's content. Returns several candidates ranked by relevance so you can disambiguate. This indexes authors who have published content here — distinct from list_known_authors, which lists hand-curated follow sets. NOTE: this resolves only kind-0 author profiles. It does NOT resolve a community's identifying pubkey — a community is defined by a kind-10222 event and frequently has no kind-0 at all. To list content shared into a community you need that community pubkey (a Nostr identifier, e.g. from the community's spec/naddr), which you pass to the `community` param of search_content / search_calendar_events. resolve_author CAN, however, find a community's posting account (e.g. a "…-Termine-Bot") when that account has a kind-0; querying that pubkey via authors:[...] returns the content it published. A wrong pick simply yields empty results.

  Parameters:

  • name (required) — string — Org or person name to resolve (e.g. "Jörg Lohrer").
  • limit — number — Max candidates (1-25, default 10).

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• resolve_publisher read-only

  Resolve an actor name (organization or person) to the EXACT spelling used in the AMB metadata, so it can be passed to the publisherName/creatorName filters of search_resources. Those filters are exact full-string matches (case-insensitive), so a guessed spelling like "Lehreladen" silently misses the stored "LEHRE LADEN". This tool free-text searches the name and returns the similar publisher/creator names found in the corpus, with the field they appear in and a resource count. Distinct from resolve_author, which resolves Nostr signing accounts (kind-0 profiles) to pubkeys — metadata publishers usually have no Nostr account at all.

  Parameters:

  • name (required) — string — Actor name as the user said it (e.g. "Lehreladen").
  • relays — array — Restrict the lookup to specific relays. Only relays returned by list_relays (default or extra) are accepted, by full URL or short name (e.g. "oersi", "sodix"). Default: the default relay set.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• search_calendar_events read-only

  Search for NIP-52 calendar events (date-based and time-based). Supports temporal filters (start/end time ranges), geohash location filtering, and hashtag filtering. Returns events from the configured calendar relay. When presenting an event to the user, render it as a markdown link: prefer the event `url` (the edufeed-app viewer at <base>/<naddr>, which shows fuller details) over `sourcePage` (the original external event page). Never construct an naddr or viewer URL yourself — use the `naddr`/`url` fields as returned.

  Parameters:

  • kinds — array — Event kinds to query (default: [31922, 31923]). 31922 = date-based, 31923 = time-based.
  • limit — number — Maximum number of results (1-250, default: 20)
  • query — string — Free-text topic for the events. Combines with a time range (startAfter/startBefore/endAfter/endBefore) in a single server-side query — e.g. "events about X in the next week" is one call. EXCEPTION: a geohash query forces the relay location index, which ignores this topic; for "events about X near a place" pass the geohash and filter the returned events by topic on the client.
  • since — number — Return events created at or after this Unix timestamp
  • until — number — Return events created at or before this Unix timestamp
  • authors — array — Filter by author pubkeys (hex format)
  • geohash — string — Geohash prefix for location-based search
  • endAfter — number — Only events ending after this Unix timestamp
  • hashtags — array — Filter by hashtags (e.g., ["meetup", "nostr"])
  • community — string — Return calendar events shared into this community (Communikey). Accepts a hex pubkey or npub; resolve a community name with resolve_author. Combines with a time range (startAfter/startBefore/endAfter/endBefore) in a single server-side query, so "events shared with X next week" is one call. EXCEPTION: a geohash query forces the relay location index, which ignores this community filter; for "shared with X near a place" pass the geohash and filter the returned events by community client-side.
  • endBefore — number — Only events ending before this Unix timestamp
  • startAfter — number — Only events starting after this Unix timestamp
  • startBefore — number — Only events starting before this Unix timestamp

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• list_calendar_authors read-only

  List known calendar event authors loaded from configured follow sets (NIP-51 kind 30000). Returns author names, pubkeys, and NIP-05 identifiers. Use the returned pubkeys with search_calendar_events(authors: [...]) to filter events by author.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

• search_passages read-only

  THE DEFAULT TOOL FOR QUESTION-SHAPED QUERIES ("wie/warum/was hilft bei X?", "how do I…?"): retrieves the best-matching fulltext passages from the corpus and returns them with citations (source resource, page, heading, source URL) — answer the user FROM the passages and cite each source. (For discovery intent — "finde/empfiehl Materialien" — use search_content instead, or afterwards to offer browsable links.) Keep `question` topic-only. Ranking is hybrid keyword+vector, so phrase the question as a topical statement that names the subject and the target group ("Friedenserziehung in der Grundschule: Einstieg in das Thema Frieden mit Kindern"), not as the user's literal sentence ("Wie kann ich …?"). Results are capped at two passages per document; a passage with only a snippet and no text has no fulltext yet — say so instead of guessing. Educational-resource passages come only from openly licensed resources (CC0, Public Domain, CC BY, CC BY-SA); other content types are not license-filtered. Scope is required but simple: with no source restriction from the user, pass the content kinds (e.g. kinds:[30142] for educational resources, [30040,30041] for publications, [30023] for articles). Route source restrictions ("nur Content von X") into the scope parameters: a metadata publisher (most organisations — resolve_publisher finds the exact spelling) goes into `search` as a QUOTED field filter, e.g. search:'publisher.name:"LEHRE LADEN"' (unquoted multi-word names match nothing); a Nostr signing account (resolve_author → pubkey) goes into `authors`. A published grimoire spell (kind 777, nevent or event id) can replace inline scope entirely; the response carries the canonical spell for whatever scope was used — publish it (e.g. via grimoire) to make the scope reusable. Spells may use $me/$contacts; they resolve to the calling user (pass `me` if the transport is anonymous). Fails rather than widening scope: an empty scope, unreachable relay (relay_unreachable — tell the user to retry), or unreachable index is a typed error, never a silently unscoped search.

  Parameters:

  • question (required) — string — The question or topic to find grounding passages for.
  • me — string — Who $me refers to (npub or hex). Defaults to the calling identity.
  • tag — object — Inline scope: one tag filter, e.g. {letter:"h", values:["<community-pk>"]}.
  • kinds — array — Inline scope: content kinds (e.g. 30142).
  • limit — number — Passages to return (1-25, default 10).
  • since — string — Inline scope: absolute Unix seconds or relative (7d, 1mo, now).
  • spell — string — Published spell: nevent, note id, or 64-hex event id.
  • until — string — Inline scope: absolute Unix seconds or relative.
  • relays — array — Relay selection (list_relays set), by full URL or short name (e.g. "oersi", "sodix"). First mapped relay is used.
  • search — string — Inline scope: NIP-50 term selecting the EVENTS in scope (distinct from question). Supports field filters; quote multi-word values: publisher.name:"LEHRE LADEN".
  • authors — array — Inline scope: Nostr event-author pubkeys (hex/npub/$me/$contacts) — resolve names via resolve_author. NOT for metadata publishers; those go into `search`.

  Hints: read-only yes · destructive no · idempotent yes · open-world no

Publisher website Repository

Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.