VectifyAI/pageindex-mcp
MCP server for PageIndex. PageIndex is a vectorless reasoning-based RAG system which uses multi-step reasoning and tree search to retrieve information like a human expert would.
Overview
VectifyAI/pageindex-mcp is a TypeScript MCP server licensed under MIT. MCP server for PageIndex. PageIndex is a vectorless reasoning-based RAG system which uses multi-step reasoning and tree search to retrieve information like a human expert would.
Ranked #560 out of 25632 indexed tools.
In the top 3% of all indexed tools.
Ecosystem
TypeScript MIT
Signal Breakdown
Stars 261
Freshness 1mo ago
Issue Health 50%
Contributors 4
Dependents 0
Forks 28
Description Detailed
License MIT
How to Improve
Freshness high impact
Dependents medium impact
Badge
[](https://agentrank-ai.com/tool/VectifyAI--pageindex-mcp) <a href="https://agentrank-ai.com/tool/VectifyAI--pageindex-mcp"><img src="https://agentrank-ai.com/api/badge/tool/VectifyAI--pageindex-mcp" alt="AgentRank"></a> Matched Queries
From the README
<div align="center">
<a href="https://pageindex.ai/mcp">
</a>
</div>
# PageIndex MCP
> If you find this repo useful, please also star our **[main PageIndex repo](https://github.com/VectifyAI/PageIndex)** ⭐
📘 [**PageIndex**](https://github.com/VectifyAI/PageIndex) is a vectorless, reasoning-based RAG system that represents documents as hierarchical **tree structures**. It enables LLMs to navigate and retrieve information through structure and **reasoning**, not vector similarity — much like a human would retrieve information using a book's index.
🔌 [**PageIndex MCP**](https://pageindex.ai/mcp) exposes this **LLM-native, in-context tree index** directly to LLMs via MCP, allowing platforms like **Claude**, **Cursor**, and other MCP-compatible agents or LLMs to reason over document structure and retrieve the right information — without vector databases.
Want to chat with long PDFs but hit context limit reached errors? Add your file to PageIndex to Read full README on GitHub →
Are you the maintainer? Claim this listing