MCP profile

Github VectifyAI Pageindex Mcp

Reasoning-based RAG system for chatting with long PDFs. Supports local and online files.

Developer ToolsPackageJavaScript/TypeScript, mcpbOpen SourceExternal

Book a demo View source

Last updated

March 16, 2026

Visibility

Public

ByRegistry

About This MCP Server

PageIndex is a vectorless, reasoning-based RAG system that generates hierarchical tree structures of documents and uses multi-step reasoning and tree search to retrieve information like a human expert would. It has the following key properties:

What Problems It Solves

If you already have a PageIndex Chat account, you can connect your MCP client directly via OAuth.
Download the .mcpb file from Releases and double-click to install. OAuth authentication is handled automatically.
If you need to upload local PDF files, you can run the local MCP server (requires Node.js ≥18.0.0):
For more details, visit PageIndex Chat.

Specifications

Status

live

Industry

Developer Tools

Hosting

Hosting Options

Package

API

Integrate this server into your application. Choose a connection method below.

Configure

Configuration

json

{
  "mcpServers": {
    "pageindex": {
      "type": "http",
      "url": "https://api.pageindex.ai/mcp",
      "headers": {
        "Authorization": "Bearer your_api_key"
      }
    }
  }
}

Performance

Usage

Quick Reference

Name: Github VectifyAI Pageindex Mcp
Function: Reasoning-based RAG system for chatting with long PDFs. Supports local and online files.
Transport: Package
Language: JavaScript/TypeScript, mcpb
Source: External (Registry)
License: Open Source