masnavi

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

{ "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; 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.