Tafsir MCP

Tafsir MCP is an open-source server built on Anthropic's Model Context Protocol (MCP). It gives any MCP-compatible AI assistant — Claude Code, Claude Desktop, VS Code, and others — direct scholarly access to Quranic text, classical commentaries, and linguistic analysis, eliminating hallucinations in language model responses about Quranic content.

All data is reviewed and certified by researchers at Tafsir Center for Quranic Studies. The database is opened read-only with strict boundary validation via Pydantic v2.

Scholarly Content

• 6,236 ayahs in Uthmani script.
• 8 tafsir sources: Tabari (d. 310H), Ibn Kathir (d. 774H), Baghawi (d. 510H), Sa'di (d. 1376H), Muyassar, and Mukhtasar in three languages (Arabic, English, Bengali).
• 77,432 words with full linguistic analysis: i'rab, sarf, root, rasm.
• 1,891 indexed roots with full occurrence statistics.
• Asbab al-nuzool with full isnad for 201 ayahs.
• Qira'at variants per ayah and word.
• Detailed statistics per surah and mushaf page.

13 Tools across 5 Categories

• Ayah: fetch text, tafsir from 8 sources in one call, asbab al-nuzool with isnad.
• Surah: full info (goals, virtues, revelation context) and statistics.
• Word: full analysis (i'rab, sarf, meaning, root, qira'at), root occurrences and stats.
• Search: fast FTS5 diacritic-free search, and LIKE search within any tafsir body.
• General: Quran-wide statistics and page-level fawaed.

Installation

For Claude Code:

claude mcp add tafsir --scope user -- uvx tafsir-mcp

Or via pip:

pip install tafsir-mcp

Works fully offline after first run — the database (~214 MB) is auto-downloaded and cached locally. A remote endpoint is also available at mcp.tafsir.net/mcp.

License: code MIT; Quranic data CC BY 4.0 with required attribution to Tafsir Center.