quran-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| QURAN_MCP_CACHE | No | Set this to change the location where texts are cached. Texts are downloaded on first use (about 1.5 MB per Quran edition, a few MB per hadith collection) into `~/.cache/quran-mcp` by default and read from disk afterwards. |
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 | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| get_versesC | Arabic text and translation of a verse or a passage: '2:255', '2:255-257', or a surah number for the whole surah (up to 300 verses). |
| list_surahsA | The 114 surahs: number, name, meaning, place of revelation, verse count. |
| search_quranA | Find verses containing every word of the query, in the translation or in the Arabic (vowel marks and accents are ignored). |
| list_translationsA | Available translations of the Quran (about 440, in 90 languages), filtered by a language name such as 'french' or 'english'. |
| get_hadithA | One hadith by its number in a collection (bukhari, muslim, abudawud, tirmidhi, nasai, ibnmajah, malik, nawawi, qudsi, dehlawi). Language: fra, eng, ara... |
| search_hadithC | Hadiths of a collection containing every word of the query. |
| prayer_timesA | Prayer times for a place and a day (YYYY-MM-DD, today by default), computed locally. timezone is an IANA name such as Europe/Brussels (the machine's zone by default). Methods: MWL, ISNA, Egypt, Makkah, Karachi, UOIF, Tehran. asr: standard or hanafi. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 7 tools
Each tool targets a distinct resource+action: reference lookup (get_verses) vs. full-text search (search_quran), hadith by number (get_hadith) vs. hadith search (search_hadith), plus distinct metadata (list_surahs, list_translations) and prayer_times. The lookup/search split is intuitive and well-communicated by the descriptions.
Six of seven tools follow a clear verb_noun pattern (get_verses, list_surahs, search_hadith, search_quran, list_translations, get_hadith). Only prayer_times deviates as a bare noun phrase, a minor but readable inconsistency.
Seven tools is well-scoped for a Quran/hadith reference server, covering retrieval, search, metadata, and prayer times without redundancy. Each tool earns its place.
The surface covers core workflows: verse retrieval, Quran search, translation listing, hadith retrieval/search, and prayer times. Gaps remain for tafsir/commentary and hadith-collection metadata, but the essential read-only lifecycle is covered.