Search transcribed Arabic Islamic lectures and curated verbatim benefits, with timestamped sources.
Maintain this server? Claim it
Call this server's tools from your browser. Nothing to install.
Requests go through mcptry because browsers can't call most MCP servers directly. Header values are sent to the server for that request only and are never stored or logged.
Tool list from our last check. Connect live to refresh it.
List treasures of one type, optionally from one lecture or one channel, newest lectures first, with paging. wassaya = advices; memorable_quotes = memorable sayings of the scholar; hadith_fawaid = benefits drawn from a hadith; tafsir_fawaid = benefits from a verse; sira_ibrah = lessons from the Sira and history; imam_sayings = sayings of earlier scholars he quotes; glad_tidings = glad tidings; diagnostic_observations = diagnoses of the Ummah's problems; qa_pairs = questions and answers; books_recommended = books he recommends
a channel id from list_channels
a lecture id (YouTube video id)
Pick your client. Values in capitals, like YOUR_TOKEN, are yours to fill in.
Run in a terminal
claude mcp add --transport http lectures https://mishkat.mssid.org/api/mcp
List treasures of one type, optionally from one lecture or one channel, newest lectures first, with paging. wassaya = advices; memorable_quotes = memorable sayings of the scholar; hadith_fawaid = benefits drawn from a hadith; tafsir_fawaid = benefits from a verse; sira_ibrah = lessons from the Sira and history; imam_sayings = sayings of earlier scholars he quotes; glad_tidings = glad tidings; diagnostic_observations = diagnoses of the Ummah's problems; qa_pairs = questions and answers; books_recommended = books he recommends
| Argument | Type | Description |
|---|---|---|
| type* | string | |
| limit | integer | |
| offset | integer | |
| channel_id | string | a channel id from list_channels |
| lecture_id | string | a lecture id (YouTube video id) |
{
"type": "object",
"required": [
"type"
],
"properties": {
"type": {
"enum": [
"wassaya",
"memorable_quotes",
"hadith_fawaid",
"tafsir_fawaid",
"sira_ibrah",
"imam_sayings",
"glad_tidings",
"diagnostic_observations",
"qa_pairs",
"books_recommended"
],
"type": "string"
},
"limit": {
"type": "integer",
"default": 20,
"maximum": 50,
"minimum": 1
},
"offset": {
"type": "integer",
"default": 0,
"minimum": 0
},
"channel_id": {
"type": "string",
"description": "a channel id from list_channels"
},
"lecture_id": {
"type": "string",
"description": "a lecture id (YouTube video id)"
}
},
"additionalProperties": false
}Where in the lectures a Quran verse is recited or explained, with the verse's mushaf text (Hafs) and the tafsir benefits drawn from it.
| Argument | Type | Description |
|---|---|---|
| ayah* | integer | |
| limit | integer | |
| surah* | integer |
{
"type": "object",
"required": [
"surah",
"ayah"
],
"properties": {
"ayah": {
"type": "integer",
"maximum": 286,
"minimum": 1
},
"limit": {
"type": "integer",
"default": 10,
"maximum": 30,
"minimum": 1
},
"surah": {
"type": "integer",
"maximum": 114,
"minimum": 1
}
},
"additionalProperties": false
}A lecture's details: title, channel, length, series it belongs to, its topics with their summaries, and how many treasures of each type it holds. Use get_transcript for its words.
| Argument | Type | Description |
|---|---|---|
| lecture_id* | string |
{
"type": "object",
"required": [
"lecture_id"
],
"properties": {
"lecture_id": {
"type": "string"
}
},
"additionalProperties": false
}A topic of the map with the lecture passages filed under it (each with its summary, lecture and link).
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| topic_id* | integer |
{
"type": "object",
"required": [
"topic_id"
],
"properties": {
"limit": {
"type": "integer",
"default": 15,
"maximum": 40,
"minimum": 1
},
"topic_id": {
"type": "integer"
}
},
"additionalProperties": false
}The lecture's words in order, as numbered segments with start/end seconds (paged). Machine transcription, corrected in places. Use segment numbers from other results to read the context around a passage.
| Argument | Type | Description |
|---|---|---|
| count | integer | |
| lecture_id* | string | |
| from_segment | integer |
{
"type": "object",
"required": [
"lecture_id"
],
"properties": {
"count": {
"type": "integer",
"default": 80,
"maximum": 200,
"minimum": 1
},
"lecture_id": {
"type": "string"
},
"from_segment": {
"type": "integer",
"default": 0,
"minimum": 0
}
},
"additionalProperties": false
}One treasure in full: its verbatim text, the explanation fields (summaries, not quotations), the exact segment range in its lecture and a timestamped link.
| Argument | Type | Description |
|---|---|---|
| id* | integer | |
| type* | string |
{
"type": "object",
"required": [
"type",
"id"
],
"properties": {
"id": {
"type": "integer"
},
"type": {
"enum": [
"wassaya",
"memorable_quotes",
"hadith_fawaid",
"tafsir_fawaid",
"sira_ibrah",
"imam_sayings",
"glad_tidings",
"diagnostic_observations",
"qa_pairs",
"books_recommended"
],
"type": "string"
}
},
"additionalProperties": false
}The YouTube channels in the corpus, with how many lectures each has.
No arguments.
{
"type": "object",
"required": [],
"properties": {},
"additionalProperties": false
}Lectures in the corpus (with a transcript), optionally of one channel or whose title contains some words, newest first.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| offset | integer | |
| channel_id | string | |
| title_contains | string |
{
"type": "object",
"required": [],
"properties": {
"limit": {
"type": "integer",
"default": 20,
"maximum": 50,
"minimum": 1
},
"offset": {
"type": "integer",
"default": 0,
"minimum": 0
},
"channel_id": {
"type": "string"
},
"title_contains": {
"type": "string",
"maxLength": 100
}
},
"additionalProperties": false
}Find the passages of the lectures where the scholar speaks about a subject or answers a question. Returns verbatim passages (his words as transcribed), grouped by lecture, each with a timestamped link. Arabic queries work best. Use this first for any question about what the scholar says.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query* | string | the subject or question, preferably in Arabic |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 8,
"maximum": 20,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 300,
"description": "the subject or question, preferably in Arabic"
}
},
"additionalProperties": false
}Search the topic map built over all lectures (Arabic or English topic titles); returns topic ids for get_topic.
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query* | string |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 10,
"maximum": 30,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 100
}
},
"additionalProperties": false
}Search the curated treasures (kunuz): short verbatim spans picked from the lectures and classified. wassaya = advices; memorable_quotes = memorable sayings of the scholar; hadith_fawaid = benefits drawn from a hadith; tafsir_fawaid = benefits from a verse; sira_ibrah = lessons from the Sira and history; imam_sayings = sayings of earlier scholars he quotes; glad_tidings = glad tidings; diagnostic_observations = diagnoses of the Ummah's problems; qa_pairs = questions and answers; books_recommended = books he recommends. Matches the verbatim text (Arabic).
| Argument | Type | Description |
|---|---|---|
| limit | integer | |
| query* | string | |
| types | array | limit to these types |
{
"type": "object",
"required": [
"query"
],
"properties": {
"limit": {
"type": "integer",
"default": 20,
"maximum": 40,
"minimum": 1
},
"query": {
"type": "string",
"maxLength": 200
},
"types": {
"type": "array",
"items": {
"enum": [
"wassaya",
"memorable_quotes",
"hadith_fawaid",
"tafsir_fawaid",
"sira_ibrah",
"imam_sayings",
"glad_tidings",
"diagnostic_observations",
"qa_pairs",
"books_recommended"
],
"type": "string"
},
"description": "limit to these types"
}
},
"additionalProperties": false
}We read every tool's name, description and inputs the way the model will, looking for instructions hidden from you. A clean result means no warning signs, not a guarantee. Scanned Nov 20, 2026.