# PageIndex MCP

> Vectorless tree-index RAG over long PDFs — freemium MCP for agents

**Category:** AI Agents  
**Pricing:** freemium  
**URL:** https://pageindex.ai/mcp  
**GitHub:** https://github.com/VectifyAI/pageindex-mcp  
**Added:** 2026-09-19

---

## The Hook

PageIndex MCP exposes vectorless, reasoning-based document trees to Claude/Cursor and other MCP clients — navigate long PDFs like a human using a book index, not top-k chunks.

## What's Good

MIT MCP surface over PageIndex (VectifyAI/PageIndex also MIT). Hierarchical tree index + multi-step reasoning retrieval without a vector DB. Hosted MCP with API key or App OAuth; free allowance advertised at 1000 pages with unlimited conversations for the chat path. Fits agents that blow context on long PDFs.

## The Catch

Hosted MCP needs a PageIndex API key; self-host the core repo if you refuse the cloud. Vs Supermemory / Mem0 / classic vector RAG: this is document-tree reasoning retrieval, not long-term agent memory. Free page quota is a soft ceiling — verify current Dashboard limits before treating it as unlimited corpus ingest.

## Verdict

Freemium vectorless PDF RAG via MCP. Tree search over long docs; not a general agent memory store.