QUL MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| QUL_PART_CHARS | No | Maximum size in characters of each part when long tafsir is split into numbered parts, so each response fits within MCP clients' output limits. Defaults to about 30,000 characters. | 30000 |
| QUL_API_BASE_URL | No | Base URL of the QUL API to use, to point at another QUL instance, for example a local one at http://localhost:3000/api/v1. | https://qul.tarteel.ai/api/v1 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Read-only access to the Quranic Universal Library (QUL) by Tarteel: Quran text in many scripts, translations, tafsirs, word-by-word data, and recitation audio with ayah timings. Ayahs are identified by keys like "2:255". Find translation, tafsir and recitation IDs with qul_list_resources before requesting them by ID. Never paraphrase Quran text or translations as if quoting: quote what the tools return and name the translation or tafsir it came from.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| qul_list_chaptersA | List all 114 surahs with Arabic and transliterated names, translated name, verse count and revelation place. |
| qul_get_chapterA | Get details for one surah: names, verse count, revelation place and order, mushaf page range. |
| qul_get_versesA | Get the Arabic text of one ayah or a range inside a surah, optionally with translations and word-by-word data. For a single ayah pass the same key as from and to, e.g. from "2:255". |
| qul_list_resourcesA | List available translations, tafsirs, languages, or recitations, with the IDs other tools take. Use language and query to narrow the list; translations alone number about 200. |
| qul_get_translationsA | Get translations from one translation for a range of ayahs, or from several translations for one ayah. Pass resource_id with from/to for a passage, or omit resource_id to compare translations of a single ayah. |
| qul_get_tafsirA | Get tafsir (commentary) for an ayah. Pass resource_id for one tafsir (optionally over a range), or omit it to get several tafsirs for one ayah. Tafsir entries often cover a group of ayahs; see the verses field. Text is always complete: long tafsir comes in numbered parts, and the response's next.call says how to get the next one. |
| qul_get_audioA | Get audio URLs for a recitation. For a surah_recitation pass chapter; for an ayah_recitation pass chapter and optionally ayah. Find recitation IDs with qul_list_resources. |
| qul_get_ayah_timingsA | Get start/end times (milliseconds) of each ayah inside a surah recitation's audio file, for syncing text with audio. Only works for surah_recitations with has_segments=true. |
| qul_random_ayahA | Pick a random ayah and return one translation or tafsir of it, optionally within one surah. |
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 9 tools
Each tool targets a fairly distinct resource: chapters, verses, translations, tafsir, audio, timings, resource listings, and a random ayah. The main soft overlap is between qul_get_verses (which can include translations and word-by-word data) and qul_get_translations, plus qul_get_tafsir vs. verse text, but the descriptions explicitly steer usage (ranges/multi-translation compare vs. single ayah fetch).
All tools share the qul_ prefix and a consistent verb_noun pattern (list_chapters, get_chapter, get_verses, get_tafsir, etc.). The only deviation is qul_random_ayah, which omits the verb but remains clear and readable.
Nine tools is well within the sweet spot and each earns its place: listing, fetching, audio, timings, tafsir, translations, and discovery of resource IDs. No obviously redundant or trivial entries.
The surface covers the core Quran domain: chapters, verses (with translations and word data), tafsir, audio, ayah timings, resource discovery, and a random-ayah convenience tool. The notable gap is a text/search tool (e.g., searching verses by keyword), which agents would otherwise have to emulate client-side.