ai.masnavi/masnavi

Official13 toolsLive

by shahhoseini

Rumi's complete Masnavi (25,635 beyts) — search, quote, verify and explain. Free, no auth.

ai.masnavi/masnavi MCP Server

The ai.masnavi/masnavi Model Context Protocol (MCP) server provides access to Rumi’s complete Masnavi (25,635 beyts). It supports search, quote, verify, and explain functions. The service is described as free and requires no authentication.

🛠️ Key Features

Rumi’s complete Masnavi (25,635 beyts)
Search
Quote
Verify
Explain
Free, no auth

🚀 Use Cases

Finding passages in the complete Masnavi corpus
Retrieving and referencing quotes
Checking/validating text details via verification
Getting explanations for passages

⚡ Developer Benefits

Direct programmatic access to the Masnavi dataset
Tools aligned to quote, verify, and explain workflows
No authentication requirements

⚠️ Limitations

No additional capabilities, interfaces, or configuration details are provided in the source data

Captured live from the server via tools/list.

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.

Parameters4

query	string	required	Persian text to search for
daftar	any	optional	Restrict to a single daftar (1-6)
limit	integer	optional
offset	integer	optional

Raw schema

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

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`.

Parameters3

query	string	required	What the verse should MEAN, in any language
daftar	any	optional	Restrict to a single daftar (1-6)
limit	integer	optional

Raw schema

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

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.

Parameters6

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

Raw schema

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

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.

Parameters2

text	string	required	Candidate Rumi quote in Persian
fuzzy_threshold	number	optional

Raw schema

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

get_section

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

Parameters2

section_id	any	optional
slug	any	optional	Stable URL slug

Raw schema

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

table_of_contents

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

Parameters1

daftar

any

optional

Raw schema

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

random_beyt

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

Parameters1

daftar

any

optional

Raw schema

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

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.

Parameters4

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

Raw schema

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

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).

Parameters3

query	string	required	story title words (Persian) or a description of the story in any language
daftar	any	optional
limit	integer	optional

Raw schema

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

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'.

Parameters1

citation

string

required

Citation like 'M1:1' or 'M3:1278' or 'g:7421'.

Raw schema

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

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.

Parameters3

query	string	required	Persian text to search for
limit	integer	optional
offset	integer	optional

Raw schema

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

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.

Parameters2

query	string	required	What the ghazal should be ABOUT, in any language
limit	integer	optional

Raw schema

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

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…».

Parameters2

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

Raw schema

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

Install

Tools (13)

searchsearch_meaninglookupverifyget_sectiontable_of_contentsrandom_beytget_range

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://masnavi.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "masnavi": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://masnavi.ai/mcp"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

ai.masnavi/masnavi MCP Server

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

search

search_meaning

lookup

verify

get_section

table_of_contents

random_beyt

get_range

find_sections

explain

search_divan

search_divan_meaning

get_ghazal

Install

Remote endpoint

Related servers