# masnavi [Health: Active]

**Category:** 🔒 Security  
**Repository:** https://github.com/shahhoseini/masnavi-mcp  
**GitHub Stars:** 0  
**Views:** 1  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/masnavi

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

## Tools
Capabilities this server exposes over MCP:

- **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.
- **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`.
- **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.
- **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.
- **get_section** — Retrieve a full section (story / بخش) with all its beyts.
- **table_of_contents** — Browse the Masnavi's section list. Returns titled sections per daftar with beyt counts and ranges.
- **random_beyt** — Return a randomly-selected beyt, optionally restricted to a daftar.
- **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.
- **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).
- **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'.
- **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.
- **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.
- **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…».

## Claude Desktop Quick Installation
Remote MCP endpoint (confidence: high). Install path detected from listing signals. Add as a URL/SSE server in your client:

```json
"mcpServers": {
  "masnavi": {
    "url": "https://masnavi.ai/mcp"
  }
}
```

## Documentation & README

# masnavi.ai — Rumi's Masnavi as an MCP server

The complete **Masnavi-ye Maʿnavi** of Jalāl al-Dīn Rūmī — all **25,635 beyts**
(couplets) in 6 daftars, 972 sections — served as a free, public, read-only
**Model Context Protocol** server. Your agent can search, quote, **verify**,
and explain Rumi from the canonical text instead of inventing him.

- **Site:** https://masnavi.ai (read it in 31 languages)
- **MCP endpoint:** `https://masnavi.ai/mcp` (Streamable HTTP, no auth)
- **REST + OpenAPI:** https://masnavi.ai/api/openapi.json
- **Discovery:** https://masnavi.ai/.well-known/mcp.json · https://masnavi.ai/llms.txt
- **Docs:** https://masnavi.ai/docs

## Connect

```json
{ "mcpServers": { "masnavi": { "type": "http", "url": "https://masnavi.ai/mcp" } } }
```

Claude Code: `claude mcp add --transport http masnavi https://masnavi.ai/mcp`

## Tools (9)

| Tool | What it does |
|---|---|
| `search` | full-text search across all 25,635 beyts, ranked |
| `lookup` | a beyt by citation (`M1:1` = daftar 1, beyt 1) with neighbours |
| `verify` | is this really a line by Rumi? fuzzy-checks a quotation against the corpus |
| `get_section` | one named section (story) with all its beyts |
| `get_range` | a full multi-section story in one call (≤500 beyts) |
| `find_sections` | find a story by (Persian) title fragment |
| `table_of_contents` | the 972 sections, by daftar |
| `random_beyt` | a random couplet |
| `explain` | per-beyt commentary by named scholars |

Citations use `M{daftar}:{beyt}` (e.g. `M3:1278`). Text sourced from
[Ganjoor](https://ganjoor.net/moulavi/masnavi); the Masnavi is in the
**public domain**.

## Why

Language models routinely misattribute Persian poetry. This server exists so
agents can ground every Rumi quotation in the canonical text — search it,
cite it, and verify it — in any language.

*This repository holds the public metadata for the hosted server at
masnavi.ai; the service itself runs at the endpoint above.*