PageIndex MCP
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, allowing agents to chat with long PDFs and reason over document structure without requiring a vector database.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Chat with long PDFs using reasoning-based retrieval
- Retrieve information from documents via tree search
- Reason over document structure in MCP-compatible agents
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
https://github.com/VectifyAI/pageindex-mcp/releases/download/v1.9.0/pageindex-mcp-1.9.0.mcpb 1.9.0
{
"version": "1.9.0",
"transport": "stdio",
"fileSha256": "b634dd8a827b0578f54091e55762a025bfbe23ace5dd1cf8ebc28a680e6027f4",
"identifier": "https://github.com/VectifyAI/pageindex-mcp/releases/download/v1.9.0/pageindex-mcp-1.9.0.mcpb",
"registryType": "mcpb"
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Let your agent find its tools
Find servers like PageIndex MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.