Masnavi MCP server

explain

Get commentary (Persian + English) for a specific beyt of the Masnavi, attributed to a primary source (e.g. Abdolkarim Soroush's lectures). Returns the beyt text along with structured commentary entries. Each entry has source, author, language, body markdown, and confidence ('ai-draft' / 'reviewed' / 'verbatim'). Use this when a user asks 'what does this beyt mean' or 'what does <scholar> say about M1:1'.

Argument	Type	Description
citation*	string	Citation like 'M1:1' or 'M3:1278' or 'g:7421'.

Input schema (JSON)

{
  "type": "object",
  "title": "tool_explainArguments",
  "required": [
    "citation"
  ],
  "properties": {
    "citation": {
      "type": "string",
      "title": "Citation",
      "description": "Citation like 'M1:1' or 'M3:1278' or 'g:7421'."
    }
  }
}

find_sections

Find sections (stories) by TITLE. Exact words first (phrase, then AND-of-tokens); when NO title contains the words, falls back to MEANING matches in any language (hits carry match='meaning' + a cosine score — verify with get_section before relying on one). Each match includes `first_citation` and `last_citation` — ready-to-use canonical citations (e.g. 'M2:2608'). To read a whole multi-section story, call get_range with the FIRST match's `first_citation` as start and the LAST match's `last_citation` as end. Do NOT construct a citation from `first_beyt_global` — that is a GLOBAL index (1..25635), not a daftar-local beyt number. Example: find_sections('ابلیس معاویه', daftar=2).

Argument	Type	Description
limit	integer
query*	string	story title words (Persian) or a description of the story in any language
daftar	any

Input schema (JSON)

{
  "type": "object",
  "title": "tool_find_sectionsArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 30,
      "maximum": 100,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "title": "Query",
      "description": "story title words (Persian) or a description of the story in any language"
    },
    "daftar": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 6,
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "title": "Daftar",
      "default": null
    }
  }
}

get_ghazal

Fetch ONE complete ghazal of the Divan-e Shams by its canonical number (1..3230) or citation ('G1393' / 'G1393:2'). Returns every beyt plus prev/next ghazal numbers. Famous example: get_ghazal(1393) = «مرده بدم زنده شدم…».

Argument	Type	Description
number	any	Ghazal number, e.g. 1393
citation	any	Divan citation like 'G1393' or 'G1393:2'

Input schema (JSON)

{
  "type": "object",
  "title": "tool_get_ghazalArguments",
  "properties": {
    "number": {
      "anyOf": [
        {
          "type": "integer",
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "title": "Number",
      "default": null,
      "description": "Ghazal number, e.g. 1393"
    },
    "citation": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Citation",
      "default": null,
      "description": "Divan citation like 'G1393' or 'G1393:2'"
    }
  }
}

get_range

Fetch ALL beyts between two endpoints, inclusive, grouped by section. Use this — NOT many calls to get_section or lookup — when a user asks for a full story, a long passage, or a sequence of beyts spanning multiple sections. Endpoints are canonical citations like 'M2:2608' and 'M2:2775', or global indices via start_global / end_global. Max range: 500 beyts.

Argument	Type	Description
end	any	End citation, e.g. 'M2:2775'
start	any	Start citation, e.g. 'M2:2608'
end_global	any
start_global	any

Input schema (JSON)

{
  "type": "object",
  "title": "tool_rangeArguments",
  "properties": {
    "end": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "End",
      "default": null,
      "description": "End citation, e.g. 'M2:2775'"
    },
    "start": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Start",
      "default": null,
      "description": "Start citation, e.g. 'M2:2608'"
    },
    "end_global": {
      "anyOf": [
        {
          "type": "integer",
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "title": "End Global",
      "default": null
    },
    "start_global": {
      "anyOf": [
        {
          "type": "integer",
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "title": "Start Global",
      "default": null
    }
  }
}

get_section

Retrieve a full section (story / بخش) with all its beyts.

Argument	Type	Description
slug	any	Stable URL slug
section_id	any

Input schema (JSON)

{
  "type": "object",
  "title": "tool_get_sectionArguments",
  "properties": {
    "slug": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Slug",
      "default": null,
      "description": "Stable URL slug"
    },
    "section_id": {
      "anyOf": [
        {
          "type": "integer",
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "title": "Section Id",
      "default": null
    }
  }
}

lookup

Fetch a specific beyt by its citation (e.g. 'M3:1278'), by daftar+beyt number, or by global beyt index. Optionally include surrounding beyts for context.

Argument	Type	Description
after	integer
before	integer
daftar	any
citation	any	Citation like 'M3:1278' or 'g:7421'
beyt_global	any
beyt_in_daftar	any

Input schema (JSON)

{
  "type": "object",
  "title": "tool_lookupArguments",
  "properties": {
    "after": {
      "type": "integer",
      "title": "After",
      "default": 0,
      "maximum": 20,
      "minimum": 0
    },
    "before": {
      "type": "integer",
      "title": "Before",
      "default": 0,
      "maximum": 20,
      "minimum": 0
    },
    "daftar": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 6,
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "title": "Daftar",
      "default": null
    },
    "citation": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "title": "Citation",
      "default": null,
      "description": "Citation like 'M3:1278' or 'g:7421'"
    },
    "beyt_global": {
      "anyOf": [
        {
          "type": "integer",
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "title": "Beyt Global",
      "default": null
    },
    "beyt_in_daftar": {
      "anyOf": [
        {
          "type": "integer",
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "title": "Beyt In Daftar",
      "default": null
    }
  }
}

random_beyt

Return a randomly-selected beyt, optionally restricted to a daftar.

Argument	Type	Description
daftar	any

Input schema (JSON)

{
  "type": "object",
  "title": "tool_randomArguments",
  "properties": {
    "daftar": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 6,
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "title": "Daftar",
      "default": null
    }
  }
}

search

Full-text search across the Masnavi. Returns beyts that contain the query terms, ranked by relevance. Useful for finding where a theme, word, or phrase appears.

Argument	Type	Description
limit	integer
query*	string	Persian text to search for
daftar	any	Restrict to a single daftar (1-6)
offset	integer

Input schema (JSON)

{
  "type": "object",
  "title": "tool_searchArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10,
      "maximum": 50,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "title": "Query",
      "description": "Persian text to search for"
    },
    "daftar": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 6,
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "title": "Daftar",
      "default": null,
      "description": "Restrict to a single daftar (1-6)"
    },
    "offset": {
      "type": "integer",
      "title": "Offset",
      "default": 0,
      "minimum": 0
    }
  }
}

search_divan

Full-text search across the 34,603 beyts of the ghazals of the Divan-e Shams (Divan-e Kabir) — Rumi's lyric work, distinct from the Masnavi. Returns beyts with divan citations (G{ghazal}:{beyt}, e.g. G1393:1). Use when you know the exact Persian words; use search_divan_meaning for a theme in any language.

Argument	Type	Description
limit	integer
query*	string	Persian text to search for
offset	integer

Input schema (JSON)

{
  "type": "object",
  "title": "tool_search_divanArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10,
      "maximum": 50,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "title": "Query",
      "description": "Persian text to search for"
    },
    "offset": {
      "type": "integer",
      "title": "Offset",
      "default": 0,
      "minimum": 0
    }
  }
}

search_divan_meaning

Semantic search over the Divan-e Shams ghazals: given a theme, feeling, or idea in ANY language, returns the GHAZALS closest in meaning — each with its best-matching couplet as a preview and a cosine score. Both couplet-level and whole-ghazal vectors are searched, so a ghazal whose overall theme matches is found even when no single couplet does. Fetch a full ghazal with get_ghazal. status='unavailable' means the index is not built — fall back to search_divan.

Argument	Type	Description
limit	integer
query*	string	What the ghazal should be ABOUT, in any language

Input schema (JSON)

{
  "type": "object",
  "title": "tool_search_divan_meaningArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 8,
      "maximum": 30,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "title": "Query",
      "description": "What the ghazal should be ABOUT, in any language"
    }
  }
}

search_meaning

Semantic search: find the beyts closest in MEANING to the query, in ANY language — English, Persian, Spanish, Turkish, Arabic, … . Use this when you have a theme, feeling, or idea rather than exact Persian words (e.g. 'feeling separated from your origin' → M1:1). Each hit carries a cosine-similarity score. status='unavailable' means the vector index is not built yet — fall back to `search`.

Argument	Type	Description
limit	integer
query*	string	What the verse should MEAN, in any language
daftar	any	Restrict to a single daftar (1-6)

Input schema (JSON)

{
  "type": "object",
  "title": "tool_search_meaningArguments",
  "required": [
    "query"
  ],
  "properties": {
    "limit": {
      "type": "integer",
      "title": "Limit",
      "default": 10,
      "maximum": 50,
      "minimum": 1
    },
    "query": {
      "type": "string",
      "title": "Query",
      "description": "What the verse should MEAN, in any language"
    },
    "daftar": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 6,
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "title": "Daftar",
      "default": null,
      "description": "Restrict to a single daftar (1-6)"
    }
  }
}

table_of_contents

Browse the Masnavi's section list. Returns titled sections per daftar with beyt counts and ranges.

Argument	Type	Description
daftar	any

Input schema (JSON)

{
  "type": "object",
  "title": "tool_tocArguments",
  "properties": {
    "daftar": {
      "anyOf": [
        {
          "type": "integer",
          "maximum": 6,
          "minimum": 1
        },
        {
          "type": "null"
        }
      ],
      "title": "Daftar",
      "default": null
    }
  }
}

verify

Given a candidate quote attributed to Rumi's Masnavi, check whether it actually appears. Returns status='exact' (with citation), 'fuzzy' (with similar candidates), or 'not_found'. USE THIS BEFORE QUOTING RUMI to avoid hallucination.

Argument	Type	Description
text*	string	Candidate Rumi quote in Persian
fuzzy_threshold	number

Input schema (JSON)

{
  "type": "object",
  "title": "tool_verifyArguments",
  "required": [
    "text"
  ],
  "properties": {
    "text": {
      "type": "string",
      "title": "Text",
      "description": "Candidate Rumi quote in Persian"
    },
    "fuzzy_threshold": {
      "type": "number",
      "title": "Fuzzy Threshold",
      "default": 0.82,
      "maximum": 1,
      "minimum": 0.5
    }
  }
}

Masnavi

Try it

explain

Masnavi

Try it

explain

Tools (13)