PageIndex MCP is a reasoning-based system that allows LLMs to navigate and retrieve information from documents represented as hierarchical tree structures without using vector databases. It supports local and online PDFs for seamless interaction with long documents.
From the registry: Reasoning-based RAG system for chatting with long PDFs. Supports local and online files.

Please install the `pageindex-mcp` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **PageIndex API Key** — Create an API key at dash.pageindex.ai/api-keys (https://dash.pageindex.ai/api-keys)
Canonical MCP server config (HTTP transport):
- url: `https://api.pageindex.ai/mcp`
- headers:
- `Authorization`: `Bearer <your-api-key>`
Note: Vectorless, reasoning-based RAG for long PDFs. Free: 1000 pages. For local PDF upload, use the stdio server: npx -y @pageindex/mcp (no API key needed for OAuth flow). Unlimited conversations.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.API_KEYrequiredAuthentication key for connecting to the PageIndex MCP.AI orchestration with hive-mind swarms, neural networks, and 87 MCP tools for enterprise dev.
MCP Toolbox for Databases enables your agent to connect to your database.
MCP Toolbox for Databases enables your agent to connect to your database.