Poems for a mood, a situation or an occasion, with poets, analyses and plans to learn by heart.
Scored across 9 tools
Each tool targets a distinct resource or action: poet lookup, poem search, poem detail, analysis, collection detail, collection listing, learning plan, filter guide, and poem of the day. The only mild overlaps are get_poem (which already returns a short summary and analysis link) versus get_analysis, and about_poet's embedded poem list versus find_poems, but the descriptions make the boundaries clear enough that an agent can choose correctly.
All names are snake_case and readable, but verb conventions are mixed: get_* for three tools, list_ for one, find_ for one, and then about_poet, learn_by_heart, library_guide, poem_of_the_day follow noun-phrase or unique styles. It works, but an agent cannot infer the pattern from the name alone (e.g. about_poet vs get_poet).
Nine tools is well-scoped for a poetry library server; each tool covers a distinct entry point (search, poem, poet, collection, analysis, learning, guidance, daily poem) with no filler. Nothing feels redundant or missing at the count level.
The surface covers the full discovery lifecycle: guide/filters, search, poem detail, poet detail, collections, analysis, learning plan, and a daily poem, with links out for full text. Minor gaps exist — no direct full-text retrieval, no browse-by-mood/tag tool outside find_poems, and no poet listing — but agents can work around these via the site links.
A poet in the library by name or by slug (the last part of the poet page URL): the biography (up to about 1,500 characters) and a one-line summary of it, the number of poems, up to 10 poems with links, and the poet page.
Inputs: name, slug.
Search the library. For a situation or a wish ("I just lost my dad", "a poem to thank my mother", "something calm for a ten-year-old", "an easy first poem to learn by heart"), set what the reader needs first: need, or occasion and recipient for a poem to send, audience, easy_to_memorise, easy_to_read. Narrow it with one mood or 1–3 tags from library_guide in the poem language, and max_lines for a short poem. Words in query are looked for in the title and text and in what the poem is about, so "grief father" finds poems of a father's death. For a poem or line the user remembers, put its words in query. Returns up to 10 poems, the best fit first, with the poet, the number of lines, the opening lines (a poem of 1 to 3 lines whole), one sentence on what the poem feels like (use it to choose, it is not the poet's words) and the link. need, occasion, recipient, easy_to_memorise, easy_to_read and audience cover English, Russian and Belarusian poems. Give at least one filter. When nothing fits, or the user wants a deeper search by mood or situation, give them the Smart Search link from the result: a page of the site where they describe it in their own words.
Inputs: mood, need, tags, limit, +9 more.
The summary of a poem and the opening of its analysis (about 1,200 characters at most), with links to the summary and analysis pages, when the library has them. Written in the language of the poem.
Inputs: id (required).
One collection by its slug (from library_guide or list_collections): title, introduction, link and up to 8 of its poems with the poet, the number of lines, the opening lines (a poem of 1 to 3 lines whole), one sentence on what the poem feels like (use it to choose, it is not the poet's words) and the links.
Inputs: slug (required).
One poem by its id (from find_poems or a poem page URL): title, poet, language, the number of lines and stanzas, the opening of the text (a poem of 1 to 3 lines whole), a short summary when the library has one, and the links to the full poem, its analysis (when there is one) and the trainer to learn it by heart.
Inputs: id (required).
A plan to learn a poem by heart in a number of days (7 by default, 3 to 14): its stanzas and lines, which stanzas to learn on which day with a time estimate, the review days after, and the link to the free web trainer that does the drilling. No poem in mind: find_poems with easy_to_memorise suggests an easy first poem to learn.
Inputs: id (required), days.
What the library offers in one language, to turn a request into filters: the 8 moods (names in that language), the most used tags of that language (most used first) and its collections (title and slug). Call it to narrow find_poems (need, occasion, audience) with one mood and 1–3 tags, or to pick a collection for get_collection. For an easy first poem to learn by heart, find_poems with easy_to_memorise.
Inputs: language.
For an occasion or a feeling (a wedding, a funeral, missing someone, autumn), the library's collections of poems in a language (all languages when none is given): title, slug, a short introduction and the link. Pick the closest and call get_collection with its slug. Collections exist in English, Russian and Belarusian.
Inputs: language.
Today's poem of the day in a language (English by default): title, poet, opening lines (a poem of 1 to 3 lines whole) and link.
Inputs: language.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Multisyllabic, vowel and classic rhymes plus rhyming lines in 56 languages for lyrics and poems.
Book difficulty, reading times and ranked lists, plus your reading log, quotes and clubs.
Complete classical & world literature — search + cite exact passages, facing sources, 50+ languages.
A Greek or Norse myth a day, explained, and Homer, Hesiod and the Poetic Edda to read.
Add one secure layer between your agents and this server.
