madeenan
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| MADEENAN_API_KEY | No | Optional Madeenan API key. Without it, requests use the public service limits. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
Use these read-only tools to retrieve source text and evidence from Madeenan. Citations are retrieval results, not a ruling or a guarantee of interpretation. State uncertainty and ask a qualified scholar for religious guidance when needed.
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
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_islamic_sourcesC | Search Quran, Hadith, Tafsir, and dua sources. Returns source text and citation fields. |
| lookup_quran_referenceA | Read one Quran verse, chapter, or bounded passage by reference. |
| lookup_hadith_referenceA | Read one Hadith by collection slug and number, including grade metadata. |
| lookup_duaC | Read one dua or adhkar item by collection slug and item ID. |
| find_quote_sourceB | Find wording matches for a quote. A match does not prove authorship or meaning. |
| create_evidence_bundleB | Create a compact bundle of search results and requested source lookups. This is an evidence collection helper. It does not decide a religious ruling. |
| review_evidence_claimA | Review whether supplied evidence is relevant to a claim without verifying truth. This tool performs a basic evidence checklist. It does not certify a claim, issue a fatwa, or verify religious meaning. Include source references in the evidence list and ask a qualified scholar for interpretation. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| source_review_prompt | Prepare a cautious source review request for an MCP host. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| config_status | Return safe server configuration status. Secrets are never included. |
TDQS
Scored across 7 tools
The three lookup tools are cleanly separated by source type (dua, Quran, Hadith), and the evidence bundle/review pair serves clearly different roles (assembly vs. checklist review). The main overlap is between search_islamic_sources and find_quote_source, which both take text and return source matches; the descriptions hint at the difference (query search vs. quote wording match) but an agent could still pick the wrong one.
Every tool follows a snake_case verb_noun pattern (lookup_*, find_*, search_*, create_*, review_*), with nouns that map to the resource being touched. No mixing of conventions or vague single-word names.
Seven tools is well within the ideal range and each one earns its place: three source lookups, one cross-source search, one quote matcher, and two evidence-workflow helpers. Nothing looks like filler or a near-duplicate.
The surface covers the core lifecycle of source lookup (dua, Quran, Hadith, plus tafsir via search) and adds an evidence collection/review workflow, which is coherent for the stated purpose. Gaps remain: there is no tool to enumerate valid collection slugs or available sources, and tafsir has no direct reference lookup, so an agent must guess slugs or go through generic search.